Over the past few years, the internet of things (IoT) has advanced to connect billions of smart devices to improve quality of life. However, anomalies or malicious intrusions pose several security loopholes, leading to performance degradation and threat to data security in IoT operations. Thereby, IoT security systems must keep an eye on and restrict unwanted events from occurring in the IoT network. Recently, various technical solutions based on machine learning (ML) models have been derived towards identifying and restricting unwanted events in IoT. However, most ML-based approaches are prone to miss-classification due to inappropriate feature selection. Additionally, most ML approaches applied to intrusion detection and prevention consider supervised learning, which requires a large amount of labeled data to be trained. Consequently, such complex datasets are impossible to source in a large network like IoT. To address this problem, this proposed study introduces an efficient learning mechanism to strengthen the IoT security aspects. The proposed algorithm incorporates supervised and unsupervised approaches to improve the learning models for intrusion detection and mitigation. Compared with the related works, the experimental outcome shows that the model performs well in a benchmark dataset. It accomplishes an improved detection accuracy of approximately 99.21%.
A signature-based data security and authentication framework for internet of...IJECEIAES
This document presents a research paper that proposes a signature-based data security and authentication framework for Internet of Things (IoT) applications. The paper introduces a novel computational model that establishes a unique authentication process using a simplified encryption strategy. The model considers both local and global IoT environments and implements an authentication mechanism using challenge-response exchanges between communicating nodes. A digital signature is generated using parameters like random seeds, secret keys, prime values, and data packets. Simulation results show that the proposed system offers efficient security and data transmission performance in the presence of unknown adversaries, performing better than commonly used security solutions in vulnerable IoT environments.
Novel authentication framework for securing communication in internet-of-things IJECEIAES
Internet-of-Things (IoT) offers a big boon towards a massive network of connected devices and is considered to offer coverage to an exponential number of the smart appliance in the very near future. Owing to the nascent stage of evolution of IoT, it is shrouded by security loopholes because of various reasons. Review of existing research-based solution highlights the usage of conventional cryptographic-based solution over the traditional mechanism of data forwarding process between IoT nodes and gateway. The proposed system presents a novel solution to this problem by a model that is capable of performing a highly secured and cost-effective authentication process. The proposed system introduces Authentication Using Signature (AUS) as well as Security with Complexity Reduction (SCR) for the purpose to resist participation of any form of unknown threats. The outcome of the model shows better security strength with faster response time and energy saving of the IoT nodes.
A review on machine learning based intrusion detection system for internet of...IJECEIAES
Within an internet of things (IoT) environment, the fundamental purpose of various devices is to gather the abundant amount of data that is being generated and then transmit this data to the predetermined server over the internet. IoT connects billions of objects and the internet to communicate without human intervention. But network security and privacy issues are increasing very fast, in today's world. Because of the prevalence of technological advancement in regular activities, internet security has evolved into a necessary requirement. Because technology is integrated into every aspect of contemporary life, cyberattacks on the internet of things represent a bigger danger than attacks against traditional networks. Researchers have found that combining machine learning techniques into an intrusion detection system (IDS) is an efficient way to get beyond the limitations of conventional IDSs in an IoT context. This research presents a comprehensive literature assessment and develops an intrusion detection system that makes use of machine learning techniques to address security problems in an IoT environment. Along with a comprehensive look at the state of the art in terms of intrusion detection systems for IoT-enabled environments, this study also examines the attributes of approaches, common datasets, and existing methods utilized to construct such systems.
Network security is one of the foremost anxieties of the modern time. Over
the previous years, numerous studies have been accompanied on the
intrusion detection system. However, network security is one of the foremost
apprehensions of the modern era this is due to the speedy development and
substantial usage of altered technologies over the past period. The
vulnerabilities of these technologies security have become a main dispute
intrusion detection system is used to classify unapproved access and unusual
attacks over the secured networks. For the implementation of intrusion
detection system different approaches are used machine learning technique
is one of them. In order to comprehend the present station of application of
machine learning techniques for solving the intrusion discovery anomalies in
internet of thing (IoT) based big data this review paper conducted. Total 55
papers are summarized from 2010 and 2021 which were centering on the
manner of the single, hybrid and collaborative classifier design. This review
paper also includes some of the basic information like IoT, big data, and
machine learning approaches are discussed.
A trust based secure access control using authentication mechanism for intero...IJECEIAES
The internet of things (IoT) is a revolutionary innovation in many aspects of our society including interactions, financial activity, and global security such as the military and battlefield internet. Due to the limited energy and processing capacity of network devices, security, energy consumption, compatibility, and device heterogeneity are the long-term IoT problems. As a result, energy and security are critical for data transmission across edge and IoT networks. Existing IoT interoperability techniques need more computation time, have unreliable authentication mechanisms that break easily, lose data easily, and have low confidentiality. In this paper, a key agreement protocol-based authentication mechanism for IoT devices is offered as a solution to this issue. This system makes use of information exchange, which must be secured to prevent access by unauthorized users. Using a compact contiki/cooja simulator, the performance and design of the suggested framework are validated. The simulation findings are evaluated based on detection of malicious nodes after 60 minutes of simulation. The suggested trust method, which is based on privacy access control, reduced packet loss ratio to 0.32%, consumed 0.39% power, and had the greatest average residual energy of 0.99 mJoules at 10 nodes.
Efficient network management and security in 5G enabled internet of things us...IJECEIAES
The rise of fifth generation (5G) networks and the proliferation of internet- of-things (IoT) devices have created new opportunities for innovation and increased connectivity. However, this growth has also brought forth several challenges related to network management and security. Based on the review of literature it has been identified that majority of existing research work are limited to either addressing the network management issue or security concerns. In this paper, the proposed work has presented an integrated framework to address both network management and security concerns in 5G internet-of-things (IoT) network using a deep learning algorithm. Firstly, a joint approach of attention mechanism and long short-term memory (LSTM) model is proposed to forecast network traffic and optimization of network resources in a, service-based and user-oriented manner. The second contribution is development of reliable network attack detection system using autoencoder mechanism. Finally, a contextual model of 5G-IoT is discussed to demonstrate the scope of the proposed models quantifying the network behavior to drive predictive decision making in network resources and attack detection with performance guarantees. The experiments are conducted with respect to various statistical error analysis and other performance indicators to assess prediction capability of both traffic forecasting and attack detection model.
A Comprehensive Survey on Exiting Solution Approaches towards Security and Pr...IJECEIAES
‘Internet of Things (IoT)’emerged as an intelligent collaborative computation and communication between a set of objects capable of providing on-demand services to other objects anytime anywhere. A large-scale deployment of data-driven cloud applications as well as automated physical things such as embed electronics, software, sensors and network connectivity enables a joint ubiquitous and pervasive internet-based computing systems well capable of interacting with each other in an IoT. IoT, a well-known term and a growing trend in IT arena certainly bring a highly connected global network structure providing a lot of beneficial aspects to a user regarding business productivity, lifestyle improvement, government efficiency, etc. It also generates enormous heterogeneous and homogeneous data needed to be analyzed properly to get insight into valuable information. However, adoption of this new reality (i.e., IoT) by integrating it with the internet invites a certain challenges from security and privacy perspective. At present, a much effort has been put towards strengthening the security system in IoT still not yet found optimal solutions towards current security flaws. Therefore, the prime aim of this study is to investigate the qualitative aspects of the conventional security solution approaches in IoT. It also extracts some open research problems that could affect the future research track of IoT arena.
Multi-stage secure clusterhead selection using discrete rule-set against unkn...IJECEIAES
The document discusses a proposed multi-stage secure clusterhead selection technique for wireless sensor networks using a discrete rule-set. The technique aims to securely select clusterheads during the data aggregation process and learn the nature of communications to gain knowledge about adversary intensity. It constructs primary and secondary rule-sets to filter and select secure clusterheads based on energy, neighbors, vulnerability, vicinity and distance from adversaries. Simulation results using MEMSIC sensor nodes showed the proposed approach reduces energy consumption and improves data delivery compared to existing methods.
A signature-based data security and authentication framework for internet of...IJECEIAES
This document presents a research paper that proposes a signature-based data security and authentication framework for Internet of Things (IoT) applications. The paper introduces a novel computational model that establishes a unique authentication process using a simplified encryption strategy. The model considers both local and global IoT environments and implements an authentication mechanism using challenge-response exchanges between communicating nodes. A digital signature is generated using parameters like random seeds, secret keys, prime values, and data packets. Simulation results show that the proposed system offers efficient security and data transmission performance in the presence of unknown adversaries, performing better than commonly used security solutions in vulnerable IoT environments.
Novel authentication framework for securing communication in internet-of-things IJECEIAES
Internet-of-Things (IoT) offers a big boon towards a massive network of connected devices and is considered to offer coverage to an exponential number of the smart appliance in the very near future. Owing to the nascent stage of evolution of IoT, it is shrouded by security loopholes because of various reasons. Review of existing research-based solution highlights the usage of conventional cryptographic-based solution over the traditional mechanism of data forwarding process between IoT nodes and gateway. The proposed system presents a novel solution to this problem by a model that is capable of performing a highly secured and cost-effective authentication process. The proposed system introduces Authentication Using Signature (AUS) as well as Security with Complexity Reduction (SCR) for the purpose to resist participation of any form of unknown threats. The outcome of the model shows better security strength with faster response time and energy saving of the IoT nodes.
A review on machine learning based intrusion detection system for internet of...IJECEIAES
Within an internet of things (IoT) environment, the fundamental purpose of various devices is to gather the abundant amount of data that is being generated and then transmit this data to the predetermined server over the internet. IoT connects billions of objects and the internet to communicate without human intervention. But network security and privacy issues are increasing very fast, in today's world. Because of the prevalence of technological advancement in regular activities, internet security has evolved into a necessary requirement. Because technology is integrated into every aspect of contemporary life, cyberattacks on the internet of things represent a bigger danger than attacks against traditional networks. Researchers have found that combining machine learning techniques into an intrusion detection system (IDS) is an efficient way to get beyond the limitations of conventional IDSs in an IoT context. This research presents a comprehensive literature assessment and develops an intrusion detection system that makes use of machine learning techniques to address security problems in an IoT environment. Along with a comprehensive look at the state of the art in terms of intrusion detection systems for IoT-enabled environments, this study also examines the attributes of approaches, common datasets, and existing methods utilized to construct such systems.
Network security is one of the foremost anxieties of the modern time. Over
the previous years, numerous studies have been accompanied on the
intrusion detection system. However, network security is one of the foremost
apprehensions of the modern era this is due to the speedy development and
substantial usage of altered technologies over the past period. The
vulnerabilities of these technologies security have become a main dispute
intrusion detection system is used to classify unapproved access and unusual
attacks over the secured networks. For the implementation of intrusion
detection system different approaches are used machine learning technique
is one of them. In order to comprehend the present station of application of
machine learning techniques for solving the intrusion discovery anomalies in
internet of thing (IoT) based big data this review paper conducted. Total 55
papers are summarized from 2010 and 2021 which were centering on the
manner of the single, hybrid and collaborative classifier design. This review
paper also includes some of the basic information like IoT, big data, and
machine learning approaches are discussed.
A trust based secure access control using authentication mechanism for intero...IJECEIAES
The internet of things (IoT) is a revolutionary innovation in many aspects of our society including interactions, financial activity, and global security such as the military and battlefield internet. Due to the limited energy and processing capacity of network devices, security, energy consumption, compatibility, and device heterogeneity are the long-term IoT problems. As a result, energy and security are critical for data transmission across edge and IoT networks. Existing IoT interoperability techniques need more computation time, have unreliable authentication mechanisms that break easily, lose data easily, and have low confidentiality. In this paper, a key agreement protocol-based authentication mechanism for IoT devices is offered as a solution to this issue. This system makes use of information exchange, which must be secured to prevent access by unauthorized users. Using a compact contiki/cooja simulator, the performance and design of the suggested framework are validated. The simulation findings are evaluated based on detection of malicious nodes after 60 minutes of simulation. The suggested trust method, which is based on privacy access control, reduced packet loss ratio to 0.32%, consumed 0.39% power, and had the greatest average residual energy of 0.99 mJoules at 10 nodes.
Efficient network management and security in 5G enabled internet of things us...IJECEIAES
The rise of fifth generation (5G) networks and the proliferation of internet- of-things (IoT) devices have created new opportunities for innovation and increased connectivity. However, this growth has also brought forth several challenges related to network management and security. Based on the review of literature it has been identified that majority of existing research work are limited to either addressing the network management issue or security concerns. In this paper, the proposed work has presented an integrated framework to address both network management and security concerns in 5G internet-of-things (IoT) network using a deep learning algorithm. Firstly, a joint approach of attention mechanism and long short-term memory (LSTM) model is proposed to forecast network traffic and optimization of network resources in a, service-based and user-oriented manner. The second contribution is development of reliable network attack detection system using autoencoder mechanism. Finally, a contextual model of 5G-IoT is discussed to demonstrate the scope of the proposed models quantifying the network behavior to drive predictive decision making in network resources and attack detection with performance guarantees. The experiments are conducted with respect to various statistical error analysis and other performance indicators to assess prediction capability of both traffic forecasting and attack detection model.
A Comprehensive Survey on Exiting Solution Approaches towards Security and Pr...IJECEIAES
‘Internet of Things (IoT)’emerged as an intelligent collaborative computation and communication between a set of objects capable of providing on-demand services to other objects anytime anywhere. A large-scale deployment of data-driven cloud applications as well as automated physical things such as embed electronics, software, sensors and network connectivity enables a joint ubiquitous and pervasive internet-based computing systems well capable of interacting with each other in an IoT. IoT, a well-known term and a growing trend in IT arena certainly bring a highly connected global network structure providing a lot of beneficial aspects to a user regarding business productivity, lifestyle improvement, government efficiency, etc. It also generates enormous heterogeneous and homogeneous data needed to be analyzed properly to get insight into valuable information. However, adoption of this new reality (i.e., IoT) by integrating it with the internet invites a certain challenges from security and privacy perspective. At present, a much effort has been put towards strengthening the security system in IoT still not yet found optimal solutions towards current security flaws. Therefore, the prime aim of this study is to investigate the qualitative aspects of the conventional security solution approaches in IoT. It also extracts some open research problems that could affect the future research track of IoT arena.
Multi-stage secure clusterhead selection using discrete rule-set against unkn...IJECEIAES
The document discusses a proposed multi-stage secure clusterhead selection technique for wireless sensor networks using a discrete rule-set. The technique aims to securely select clusterheads during the data aggregation process and learn the nature of communications to gain knowledge about adversary intensity. It constructs primary and secondary rule-sets to filter and select secure clusterheads based on energy, neighbors, vulnerability, vicinity and distance from adversaries. Simulation results using MEMSIC sensor nodes showed the proposed approach reduces energy consumption and improves data delivery compared to existing methods.
This document discusses challenges and techniques for securing Internet of Things (IoT) architecture. It begins with an introduction to IoT and outlines key challenges including privacy, security, scalability, and connectivity issues that arise from the large number of interconnected devices. The document then reviews literature on techniques for securing IoT, such as using network function virtualization (NFV) and information-centric networking (ICN). It describes several proposed secure IoT architectures in detail and compares different approaches. The document concludes by discussing future directions for securing IoT architecture.
EFFECTIVE MALWARE DETECTION APPROACH BASED ON DEEP LEARNING IN CYBER-PHYSICAL...ijcsit
Cyber-physical Systems based on advanced networks interact with other networks through wireless
communication to enhance interoperability, dynamic mobility, and data supportability. The vast data is
managed through a cloud platform, vulnerable to cyber-attacks. It will threaten the customers in terms of
privacy and security as third-party users should authenticate the network. If it fails, it will create extensive
damage and threat to the established network and makes the hacker malfunction the network services
efficiently. This paper proposes a DL-based CPS approach to identify and mitigate the malware cyberphysical system attack of Denial of Service (DoS) and Distributed Denial of Service (DDoS) as it ensures
adequate decision support. At the same time, the trusted user nodes are connected to the network. It helps
to improve the privacy and authentication of the network by improving the data accuracy and Quality of
Service (QoS) in the network. Here the analysis is determined on the proposed system to improve the
network reliability and security compared to some of the existing SVM-based and Apriori-based detection
approaches.
Cyber-physical Systems based on advanced networks interact with other networks through wireless
communication to enhance interoperability, dynamic mobility, and data supportability. The vast data is
managed through a cloud platform, vulnerable to cyber-attacks. It will threaten the customers in terms of
privacy and security as third-party users should authenticate the network. If it fails, it will create extensive
damage and threat to the established network and makes the hacker malfunction the network services
efficiently. This paper proposes a DL-based CPS approach to identify and mitigate the malware cyber-
physical system attack of Denial of Service (DoS) and Distributed Denial of Service (DDoS) as it ensures
adequate decision support. At the same time, the trusted user nodes are connected to the network. It helps
to improve the privacy and authentication of the network by improving the data accuracy and Quality of
Service (QoS) in the network. Here the analysis is determined on the proposed system to improve the
network reliability and security compared to some of the existing SVM-based and Apriori-based detection
approaches.
DISTRIBUTED DENIAL OF SERVICE ATTACK DETECTION AND PREVENTION MODEL FOR IOTBA...IJNSA Journal
Defending against Distributed Denial of Service (DDoS) in the Internet of Things (IoT) computing environment is a challenging task. DDoS attacks are type of collective attack in which attackers work together to compromise internet security and services. The resource-constrained devices used in IoT deployments have made it even easier for an attacker to break, because of the vast number of vulnerable IoT devices with significant compute power. This paper proposed an ensemble machine learning (ML) model using the bagging technique to detect and prevent DDoS attacks in the IoT computing environment. We carried out an Machine Learning experiment and evaluated our proposed model with the most recent DDoS attacks (CICDoS2019) dataset. We use seven validation metrics (classification accuracy, precision rate, recall rate, f1-score, Matthews Correlation Coefficient, false negative rate and false positive rate) to evaluate the performance of the proposed model. The results obtained in our experiment shows an improved performance with an overall maximum classification accuracy of 99.75%, precision rate of 99.99%, recall rate of 99.76%, f1-score of 99.87%, Matthews Correlation Coefficient of 0.000000214, false negative rate of 0.24% and 4.42% false positive rate.
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...ijccsa
This document summarizes a research paper on privacy-preserving techniques for IoT data in cloud environments. It introduces two differential privacy algorithms: 1) Generic differential privacy (GenDP) which provides generalized privacy protection for homogeneous and heterogeneous IoT metadata through data portioning. 2) Cluster-based differential privacy which groups similar data into clusters before defining classifiers to validate privacy. The paper evaluates these techniques and finds the cluster-based approach offers better security than customized interactive algorithms while maintaining data utility. Overall, the study presents new differential privacy methods for anonymizing IoT metadata stored in the cloud.
IoT Network Attack Detection using Supervised Machine LearningCSCJournals
The use of supervised learning algorithms to detect malicious traffic can be valuable in designing intrusion detection systems and ascertaining security risks. The Internet of things (IoT) refers to the billions of physical, electronic devices around the world that are often connected over the Internet. The growth of IoT systems comes at the risk of network attacks such as denial of service (DoS) and spoofing. In this research, we perform various supervised feature selection methods and employ three classifiers on IoT network data. The classifiers predict with high accuracy if the network traffic against the IoT device was malicious or benign. We compare the feature selection methods to arrive at the best that can be used for network intrusion prediction.
IoT Guardian: A Novel Feature Discovery and Cooperative Game Theory Empowered...IJCNCJournal
Cyber intrusion attacks increasingly target the Internet of Things (IoT) ecosystem, exploiting vulnerable devices and networks. Malicious activities must be identified early to minimize damage and mitigate threats. Using actual benign and attack traffic from the CICIoT2023 dataset, this WORK aims to evaluate and benchmark machine-learning techniques for IoT intrusion detection. There are four main phases to the system. First, the CICIoT2023 dataset is refined to remove irrelevant features and clean up missing and duplicate data. The second phase employs statistical models and artificial intelligence to discover novel features. The most significant features are then selected in the third phase based on cooperative game theory. Using the original CICIoT2023 dataset and a dataset containing only novel features, we train and evaluate a variety of machine learning classifiers. On the original dataset, Random Forest achieved the highest accuracy of 99%. Still, with novel features, Random Forest's performance dropped only slightly (96%) while other models achieved significantly lower accuracy. As a whole, the work contributes substantial contributions to tailored feature engineering, feature selection, and rigorous benchmarking of IoT intrusion detection techniques. IoT networks and devices face continuously evolving threats, making it necessary to develop robust intrusion detection systems.
IoT Guardian: A Novel Feature Discovery and Cooperative Game Theory Empowered...IJCNCJournal
Cyber intrusion attacks increasingly target the Internet of Things (IoT) ecosystem, exploiting vulnerable devices and networks. Malicious activities must be identified early to minimize damage and mitigate threats. Using actual benign and attack traffic from the CICIoT2023 dataset, this WORK aims to evaluate and benchmark machine-learning techniques for IoT intrusion detection. There are four main phases to the system. First, the CICIoT2023 dataset is refined to remove irrelevant features and clean up missing and duplicate data. The second phase employs statistical models and artificial intelligence to discover novel features. The most significant features are then selected in the third phase based on cooperative game theory. Using the original CICIoT2023 dataset and a dataset containing only novel features, we train and evaluate a variety of machine learning classifiers. On the original dataset, Random Forest achieved the highest accuracy of 99%. Still, with novel features, Random Forest's performance dropped only slightly (96%) while other models achieved significantly lower accuracy. As a whole, the work contributes substantial contributions to tailored feature engineering, feature selection, and rigorous benchmarking of IoT intrusion detection techniques. IoT networks and devices face continuously evolving threats, making it necessary to develop robust intrusion detection systems.
DDOS ATTACK DETECTION ON INTERNET OF THINGS USING UNSUPERVISED ALGORITHMSijfls
The increase in the deployment of IoT networks has improved productivity of humans and organisations.
However, IoT networks are increasingly becoming platforms for launching DDoS attacks due to inherent
weaker security and resource-constrained nature of IoT devices. This paper focusses on detecting DDoS
attack in IoT networks by classifying incoming network packets on the transport layer as either
“Suspicious” or “Benign” using unsupervised machine learning algorithms. In this work, two deep
learning algorithms and two clustering algorithms were independently trained for mitigating DDoS
attacks. We lay emphasis on exploitation based DDOS attacks which include TCP SYN-Flood attacks and
UDP-Lag attacks. We use Mirai, BASHLITE and CICDDoS2019 dataset in training the algorithms during
the experimentation phase. The accuracy score and normalized-mutual-information score are used to
quantify the classification performance of the four algorithms. Our results show that the autoencoder
performed overall best with the highest accuracy across all the datasets.
DDoS Attack Detection on Internet o Things using Unsupervised Algorithmsijfls
The increase in the deployment of IoT networks has improved productivity of humans and organisations. However, IoT networks are increasingly becoming platforms for launching DDoS attacks due to inherent weaker security and resource-constrained nature of IoT devices. This paper focusses on detecting DDoS attack in IoT networks by classifying incoming network packets on the transport layer as either “Suspicious” or “Benign” using unsupervised machine learning algorithms. In this work, two deep learning algorithms and two clustering algorithms were independently trained for mitigating DDoS attacks. We lay emphasis on exploitation based DDOS attacks which include TCP SYN-Flood attacks and UDP-Lag attacks. We use Mirai, BASHLITE and CICDDoS2019 dataset in training the algorithms during the experimentation phase. The accuracy score and normalized-mutual-information score are used to quantify the classification performance of the four algorithms. Our results show that the autoencoder performed overall best with the highest accuracy across all the datasets.
A new algorithm to enhance security against cyber threats for internet of thi...IJECEIAES
One major problem is detecting the unsuitability of traffic caused by a distributed denial of services (DDoS) attack produced by third party nodes, such as smart phones and other handheld Wi-Fi devices. During the transmission between the devices, there are rising in the number of cyber attacks on systems by using negligible packets, which lead to suspension of the services between source and destination, and can find the vulnerabilities on the network. These vulnerable issues have led to a reduction in the reliability of networks and a reduction in consumer confidence. In this paper, we will introduce a new algorithm called rout attack with detection algorithm (RAWD) to reduce the affect of any attack by checking the packet injection, and to avoid number of cyber attacks being received by the destination and transferred through a determined path or alternative path based on the problem. The proposed algorithm will forward the real time traffic to the required destination from a new alternative backup path which is computed by it before the attacked occurred. The results have showed an improvement when the attack occurred and the alternative path has used to make sure the continuity of receiving the data to the main destination without any affection.
Detecting network attacks model based on a convolutional neural network IJECEIAES
Due to the increasing use of networks at present, Internet systems have raised many security problems, and statistics indicate that the rate of attacks or intrusions has increased excessively annually, and in the event of any malicious attack on network vulnerabilities or information systems, it may lead to serious disasters, violating policies on network security, i.e., “confidentiality, integrity, and availability” (CIA). Therefore, many detection systems, such as the intrusion detection system, appeared. In this paper, we built a system that detects network attacks using the latest machine learning algorithms and a convolutional neural network based on a dataset of the CSE-CIC-IDS2018. It is a recent dataset that contains a set of common and recent attacks. The detection rate is 99.7%, distinguishing between aggressive attacks and natural assertiveness.
Privacy-aware secured discrete framework in wireless sensor networkIJECEIAES
Rapid expansion of wireless sensor network-internet of things (WSN-IoT) in terms of application and technologies has led to wide research considering efficiency and security aspects. Considering the efficiency approach such as data aggregation along with consensus mechanism has been one of the efficient and secure approaches, however, privacy has been one of major concern and it remains an open issue due to low classification and high misclassification rate. This research work presents the privacy and reliable aware discrete (PRD-aggregation) framework to protect and secure the privacy of the node. It works by initializing the particular variable for each node and defining the threshold; further nodes update their state through the functions, and later consensus is developed among the sensor nodes, which further updates. The novelty of PRD is discretized transmission for efficiency and security. PRD-aggregation offers reliability through efficient termination criteria and avoidance of transmission failure. PRD-aggregation framework is evaluated considering the number of deceptive nodes for securing the node in the network. Furthermore, comparative analysis proves the marginal improvisation in terms of discussed parameter against the existing protocol.
This document summarizes research on Internet of Things (IoT) malware based on a literature review. It defines IoT and IoT malware, categorizes common types of IoT malware, and discusses platforms and operating systems that are targets for IoT malware. The document analyzes reference models for IoT security and surveys recent studies on malware affecting popular mobile and embedded operating systems like Android, iOS, ARM mbed OS, and TinyOS.
Malware threat analysis techniques and approaches for IoT applications: a reviewjournalBEEI
Internet of things (IoT) is a concept that has been widely used to improve business efficiency and customer’s experience. It involves resource constrained devices connecting to each other with a capability of sending data, and some with receiving data at the same time. The IoT environment enhances user experience by giving room to a large number of smart devices to connect and share information. However, with the sophistication of technology has resulted in IoT applications facing with malware threat. Therefore, it becomes highly imperative to give an understanding of existing state-of-the-art techniques developed to address malware threat in IoT applications. In this paper, we studied extensively the adoption of static, dynamic and hybrid malware analyses in proffering solution to the security problems plaguing different IoT applications. The success of the reviewed analysis techniques were observed through case studies from smart homes, smart factories, smart gadgets and IoT application protocols. This study gives a better understanding of the holistic approaches to malware threats in IoT applications and the way forward for strengthening the protection defense in IoT applications.
Io t security_review_blockchain_solutionsShyam Goyal
This document reviews security issues related to the Internet of Things (IoT) and potential blockchain solutions. It presents a survey of emerging topics in IoT security and blockchain technology. The document maps major IoT security issues to possible solutions and reviews how blockchain could help address challenging security problems in IoT. It also identifies open challenges for IoT security.
A Novel Security Approach for Communication using IOTIJEACS
The Internet of Things (IOT) is the arrangement of physical articles or "things" introduced with equipment, programming, sensors, and framework accessibility, which enables these things to accumulate and exchange data. Here outlining security convention for the Internet of Things, and execution of this relating security convention on the inserted gadgets. This convention will cover the honesty of messages and verification of every customer by giving a productive confirmation component. By this venture the protected correspondence is executed on implanted gadgets.
an efficient spam detection technique for io t devices using machine learningVenkat Projects
The document proposes a machine learning framework to detect spam on IoT devices. It evaluates five machine learning models on a dataset of IoT device inputs and features to compute a "spamicity score" for each device. This score indicates how trustworthy a device is based on various parameters. The results show the proposed technique is effective at spam detection compared to existing approaches.
CICS: Cloud–Internet Communication Security Framework for the Internet of Sma...AlAtfat
This document proposes a Cloud-Internet Communication Security (CICS) framework to provide secure communication among smart devices connected to the internet. The framework has four layers - a presentation layer on smart devices, a communication security layer providing encryption/decryption, a ubiquitous network layer, and a cloud layer. The cloud layer collects encrypted data from devices, processes it, and stores it securely. This framework aims to address security challenges like attacks that could disrupt services or cause denial of service when smart devices communicate using cloud computing.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Contenu connexe
Similaire à An efficient security framework for intrusion detection and prevention in internet-of-things using machine learning technique
This document discusses challenges and techniques for securing Internet of Things (IoT) architecture. It begins with an introduction to IoT and outlines key challenges including privacy, security, scalability, and connectivity issues that arise from the large number of interconnected devices. The document then reviews literature on techniques for securing IoT, such as using network function virtualization (NFV) and information-centric networking (ICN). It describes several proposed secure IoT architectures in detail and compares different approaches. The document concludes by discussing future directions for securing IoT architecture.
EFFECTIVE MALWARE DETECTION APPROACH BASED ON DEEP LEARNING IN CYBER-PHYSICAL...ijcsit
Cyber-physical Systems based on advanced networks interact with other networks through wireless
communication to enhance interoperability, dynamic mobility, and data supportability. The vast data is
managed through a cloud platform, vulnerable to cyber-attacks. It will threaten the customers in terms of
privacy and security as third-party users should authenticate the network. If it fails, it will create extensive
damage and threat to the established network and makes the hacker malfunction the network services
efficiently. This paper proposes a DL-based CPS approach to identify and mitigate the malware cyberphysical system attack of Denial of Service (DoS) and Distributed Denial of Service (DDoS) as it ensures
adequate decision support. At the same time, the trusted user nodes are connected to the network. It helps
to improve the privacy and authentication of the network by improving the data accuracy and Quality of
Service (QoS) in the network. Here the analysis is determined on the proposed system to improve the
network reliability and security compared to some of the existing SVM-based and Apriori-based detection
approaches.
Cyber-physical Systems based on advanced networks interact with other networks through wireless
communication to enhance interoperability, dynamic mobility, and data supportability. The vast data is
managed through a cloud platform, vulnerable to cyber-attacks. It will threaten the customers in terms of
privacy and security as third-party users should authenticate the network. If it fails, it will create extensive
damage and threat to the established network and makes the hacker malfunction the network services
efficiently. This paper proposes a DL-based CPS approach to identify and mitigate the malware cyber-
physical system attack of Denial of Service (DoS) and Distributed Denial of Service (DDoS) as it ensures
adequate decision support. At the same time, the trusted user nodes are connected to the network. It helps
to improve the privacy and authentication of the network by improving the data accuracy and Quality of
Service (QoS) in the network. Here the analysis is determined on the proposed system to improve the
network reliability and security compared to some of the existing SVM-based and Apriori-based detection
approaches.
DISTRIBUTED DENIAL OF SERVICE ATTACK DETECTION AND PREVENTION MODEL FOR IOTBA...IJNSA Journal
Defending against Distributed Denial of Service (DDoS) in the Internet of Things (IoT) computing environment is a challenging task. DDoS attacks are type of collective attack in which attackers work together to compromise internet security and services. The resource-constrained devices used in IoT deployments have made it even easier for an attacker to break, because of the vast number of vulnerable IoT devices with significant compute power. This paper proposed an ensemble machine learning (ML) model using the bagging technique to detect and prevent DDoS attacks in the IoT computing environment. We carried out an Machine Learning experiment and evaluated our proposed model with the most recent DDoS attacks (CICDoS2019) dataset. We use seven validation metrics (classification accuracy, precision rate, recall rate, f1-score, Matthews Correlation Coefficient, false negative rate and false positive rate) to evaluate the performance of the proposed model. The results obtained in our experiment shows an improved performance with an overall maximum classification accuracy of 99.75%, precision rate of 99.99%, recall rate of 99.76%, f1-score of 99.87%, Matthews Correlation Coefficient of 0.000000214, false negative rate of 0.24% and 4.42% false positive rate.
SECURITY AND PRIVACY AWARE PROGRAMMING MODEL FOR IOT APPLICATIONS IN CLOUD EN...ijccsa
This document summarizes a research paper on privacy-preserving techniques for IoT data in cloud environments. It introduces two differential privacy algorithms: 1) Generic differential privacy (GenDP) which provides generalized privacy protection for homogeneous and heterogeneous IoT metadata through data portioning. 2) Cluster-based differential privacy which groups similar data into clusters before defining classifiers to validate privacy. The paper evaluates these techniques and finds the cluster-based approach offers better security than customized interactive algorithms while maintaining data utility. Overall, the study presents new differential privacy methods for anonymizing IoT metadata stored in the cloud.
IoT Network Attack Detection using Supervised Machine LearningCSCJournals
The use of supervised learning algorithms to detect malicious traffic can be valuable in designing intrusion detection systems and ascertaining security risks. The Internet of things (IoT) refers to the billions of physical, electronic devices around the world that are often connected over the Internet. The growth of IoT systems comes at the risk of network attacks such as denial of service (DoS) and spoofing. In this research, we perform various supervised feature selection methods and employ three classifiers on IoT network data. The classifiers predict with high accuracy if the network traffic against the IoT device was malicious or benign. We compare the feature selection methods to arrive at the best that can be used for network intrusion prediction.
IoT Guardian: A Novel Feature Discovery and Cooperative Game Theory Empowered...IJCNCJournal
Cyber intrusion attacks increasingly target the Internet of Things (IoT) ecosystem, exploiting vulnerable devices and networks. Malicious activities must be identified early to minimize damage and mitigate threats. Using actual benign and attack traffic from the CICIoT2023 dataset, this WORK aims to evaluate and benchmark machine-learning techniques for IoT intrusion detection. There are four main phases to the system. First, the CICIoT2023 dataset is refined to remove irrelevant features and clean up missing and duplicate data. The second phase employs statistical models and artificial intelligence to discover novel features. The most significant features are then selected in the third phase based on cooperative game theory. Using the original CICIoT2023 dataset and a dataset containing only novel features, we train and evaluate a variety of machine learning classifiers. On the original dataset, Random Forest achieved the highest accuracy of 99%. Still, with novel features, Random Forest's performance dropped only slightly (96%) while other models achieved significantly lower accuracy. As a whole, the work contributes substantial contributions to tailored feature engineering, feature selection, and rigorous benchmarking of IoT intrusion detection techniques. IoT networks and devices face continuously evolving threats, making it necessary to develop robust intrusion detection systems.
IoT Guardian: A Novel Feature Discovery and Cooperative Game Theory Empowered...IJCNCJournal
Cyber intrusion attacks increasingly target the Internet of Things (IoT) ecosystem, exploiting vulnerable devices and networks. Malicious activities must be identified early to minimize damage and mitigate threats. Using actual benign and attack traffic from the CICIoT2023 dataset, this WORK aims to evaluate and benchmark machine-learning techniques for IoT intrusion detection. There are four main phases to the system. First, the CICIoT2023 dataset is refined to remove irrelevant features and clean up missing and duplicate data. The second phase employs statistical models and artificial intelligence to discover novel features. The most significant features are then selected in the third phase based on cooperative game theory. Using the original CICIoT2023 dataset and a dataset containing only novel features, we train and evaluate a variety of machine learning classifiers. On the original dataset, Random Forest achieved the highest accuracy of 99%. Still, with novel features, Random Forest's performance dropped only slightly (96%) while other models achieved significantly lower accuracy. As a whole, the work contributes substantial contributions to tailored feature engineering, feature selection, and rigorous benchmarking of IoT intrusion detection techniques. IoT networks and devices face continuously evolving threats, making it necessary to develop robust intrusion detection systems.
DDOS ATTACK DETECTION ON INTERNET OF THINGS USING UNSUPERVISED ALGORITHMSijfls
The increase in the deployment of IoT networks has improved productivity of humans and organisations.
However, IoT networks are increasingly becoming platforms for launching DDoS attacks due to inherent
weaker security and resource-constrained nature of IoT devices. This paper focusses on detecting DDoS
attack in IoT networks by classifying incoming network packets on the transport layer as either
“Suspicious” or “Benign” using unsupervised machine learning algorithms. In this work, two deep
learning algorithms and two clustering algorithms were independently trained for mitigating DDoS
attacks. We lay emphasis on exploitation based DDOS attacks which include TCP SYN-Flood attacks and
UDP-Lag attacks. We use Mirai, BASHLITE and CICDDoS2019 dataset in training the algorithms during
the experimentation phase. The accuracy score and normalized-mutual-information score are used to
quantify the classification performance of the four algorithms. Our results show that the autoencoder
performed overall best with the highest accuracy across all the datasets.
DDoS Attack Detection on Internet o Things using Unsupervised Algorithmsijfls
The increase in the deployment of IoT networks has improved productivity of humans and organisations. However, IoT networks are increasingly becoming platforms for launching DDoS attacks due to inherent weaker security and resource-constrained nature of IoT devices. This paper focusses on detecting DDoS attack in IoT networks by classifying incoming network packets on the transport layer as either “Suspicious” or “Benign” using unsupervised machine learning algorithms. In this work, two deep learning algorithms and two clustering algorithms were independently trained for mitigating DDoS attacks. We lay emphasis on exploitation based DDOS attacks which include TCP SYN-Flood attacks and UDP-Lag attacks. We use Mirai, BASHLITE and CICDDoS2019 dataset in training the algorithms during the experimentation phase. The accuracy score and normalized-mutual-information score are used to quantify the classification performance of the four algorithms. Our results show that the autoencoder performed overall best with the highest accuracy across all the datasets.
A new algorithm to enhance security against cyber threats for internet of thi...IJECEIAES
One major problem is detecting the unsuitability of traffic caused by a distributed denial of services (DDoS) attack produced by third party nodes, such as smart phones and other handheld Wi-Fi devices. During the transmission between the devices, there are rising in the number of cyber attacks on systems by using negligible packets, which lead to suspension of the services between source and destination, and can find the vulnerabilities on the network. These vulnerable issues have led to a reduction in the reliability of networks and a reduction in consumer confidence. In this paper, we will introduce a new algorithm called rout attack with detection algorithm (RAWD) to reduce the affect of any attack by checking the packet injection, and to avoid number of cyber attacks being received by the destination and transferred through a determined path or alternative path based on the problem. The proposed algorithm will forward the real time traffic to the required destination from a new alternative backup path which is computed by it before the attacked occurred. The results have showed an improvement when the attack occurred and the alternative path has used to make sure the continuity of receiving the data to the main destination without any affection.
Detecting network attacks model based on a convolutional neural network IJECEIAES
Due to the increasing use of networks at present, Internet systems have raised many security problems, and statistics indicate that the rate of attacks or intrusions has increased excessively annually, and in the event of any malicious attack on network vulnerabilities or information systems, it may lead to serious disasters, violating policies on network security, i.e., “confidentiality, integrity, and availability” (CIA). Therefore, many detection systems, such as the intrusion detection system, appeared. In this paper, we built a system that detects network attacks using the latest machine learning algorithms and a convolutional neural network based on a dataset of the CSE-CIC-IDS2018. It is a recent dataset that contains a set of common and recent attacks. The detection rate is 99.7%, distinguishing between aggressive attacks and natural assertiveness.
Privacy-aware secured discrete framework in wireless sensor networkIJECEIAES
Rapid expansion of wireless sensor network-internet of things (WSN-IoT) in terms of application and technologies has led to wide research considering efficiency and security aspects. Considering the efficiency approach such as data aggregation along with consensus mechanism has been one of the efficient and secure approaches, however, privacy has been one of major concern and it remains an open issue due to low classification and high misclassification rate. This research work presents the privacy and reliable aware discrete (PRD-aggregation) framework to protect and secure the privacy of the node. It works by initializing the particular variable for each node and defining the threshold; further nodes update their state through the functions, and later consensus is developed among the sensor nodes, which further updates. The novelty of PRD is discretized transmission for efficiency and security. PRD-aggregation offers reliability through efficient termination criteria and avoidance of transmission failure. PRD-aggregation framework is evaluated considering the number of deceptive nodes for securing the node in the network. Furthermore, comparative analysis proves the marginal improvisation in terms of discussed parameter against the existing protocol.
This document summarizes research on Internet of Things (IoT) malware based on a literature review. It defines IoT and IoT malware, categorizes common types of IoT malware, and discusses platforms and operating systems that are targets for IoT malware. The document analyzes reference models for IoT security and surveys recent studies on malware affecting popular mobile and embedded operating systems like Android, iOS, ARM mbed OS, and TinyOS.
Malware threat analysis techniques and approaches for IoT applications: a reviewjournalBEEI
Internet of things (IoT) is a concept that has been widely used to improve business efficiency and customer’s experience. It involves resource constrained devices connecting to each other with a capability of sending data, and some with receiving data at the same time. The IoT environment enhances user experience by giving room to a large number of smart devices to connect and share information. However, with the sophistication of technology has resulted in IoT applications facing with malware threat. Therefore, it becomes highly imperative to give an understanding of existing state-of-the-art techniques developed to address malware threat in IoT applications. In this paper, we studied extensively the adoption of static, dynamic and hybrid malware analyses in proffering solution to the security problems plaguing different IoT applications. The success of the reviewed analysis techniques were observed through case studies from smart homes, smart factories, smart gadgets and IoT application protocols. This study gives a better understanding of the holistic approaches to malware threats in IoT applications and the way forward for strengthening the protection defense in IoT applications.
Io t security_review_blockchain_solutionsShyam Goyal
This document reviews security issues related to the Internet of Things (IoT) and potential blockchain solutions. It presents a survey of emerging topics in IoT security and blockchain technology. The document maps major IoT security issues to possible solutions and reviews how blockchain could help address challenging security problems in IoT. It also identifies open challenges for IoT security.
A Novel Security Approach for Communication using IOTIJEACS
The Internet of Things (IOT) is the arrangement of physical articles or "things" introduced with equipment, programming, sensors, and framework accessibility, which enables these things to accumulate and exchange data. Here outlining security convention for the Internet of Things, and execution of this relating security convention on the inserted gadgets. This convention will cover the honesty of messages and verification of every customer by giving a productive confirmation component. By this venture the protected correspondence is executed on implanted gadgets.
an efficient spam detection technique for io t devices using machine learningVenkat Projects
The document proposes a machine learning framework to detect spam on IoT devices. It evaluates five machine learning models on a dataset of IoT device inputs and features to compute a "spamicity score" for each device. This score indicates how trustworthy a device is based on various parameters. The results show the proposed technique is effective at spam detection compared to existing approaches.
CICS: Cloud–Internet Communication Security Framework for the Internet of Sma...AlAtfat
This document proposes a Cloud-Internet Communication Security (CICS) framework to provide secure communication among smart devices connected to the internet. The framework has four layers - a presentation layer on smart devices, a communication security layer providing encryption/decryption, a ubiquitous network layer, and a cloud layer. The cloud layer collects encrypted data from devices, processes it, and stores it securely. This framework aims to address security challenges like attacks that could disrupt services or cause denial of service when smart devices communicate using cloud computing.
Similaire à An efficient security framework for intrusion detection and prevention in internet-of-things using machine learning technique (20)
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Neural network optimizer of proportional-integral-differential controller par...IJECEIAES
Wide application of proportional-integral-differential (PID)-regulator in industry requires constant improvement of methods of its parameters adjustment. The paper deals with the issues of optimization of PID-regulator parameters with the use of neural network technology methods. A methodology for choosing the architecture (structure) of neural network optimizer is proposed, which consists in determining the number of layers, the number of neurons in each layer, as well as the form and type of activation function. Algorithms of neural network training based on the application of the method of minimizing the mismatch between the regulated value and the target value are developed. The method of back propagation of gradients is proposed to select the optimal training rate of neurons of the neural network. The neural network optimizer, which is a superstructure of the linear PID controller, allows increasing the regulation accuracy from 0.23 to 0.09, thus reducing the power consumption from 65% to 53%. The results of the conducted experiments allow us to conclude that the created neural superstructure may well become a prototype of an automatic voltage regulator (AVR)-type industrial controller for tuning the parameters of the PID controller.
An improved modulation technique suitable for a three level flying capacitor ...IJECEIAES
This research paper introduces an innovative modulation technique for controlling a 3-level flying capacitor multilevel inverter (FCMLI), aiming to streamline the modulation process in contrast to conventional methods. The proposed
simplified modulation technique paves the way for more straightforward and
efficient control of multilevel inverters, enabling their widespread adoption and
integration into modern power electronic systems. Through the amalgamation of
sinusoidal pulse width modulation (SPWM) with a high-frequency square wave
pulse, this controlling technique attains energy equilibrium across the coupling
capacitor. The modulation scheme incorporates a simplified switching pattern
and a decreased count of voltage references, thereby simplifying the control
algorithm.
A review on features and methods of potential fishing zoneIJECEIAES
This review focuses on the importance of identifying potential fishing zones in seawater for sustainable fishing practices. It explores features like sea surface temperature (SST) and sea surface height (SSH), along with classification methods such as classifiers. The features like SST, SSH, and different classifiers used to classify the data, have been figured out in this review study. This study underscores the importance of examining potential fishing zones using advanced analytical techniques. It thoroughly explores the methodologies employed by researchers, covering both past and current approaches. The examination centers on data characteristics and the application of classification algorithms for classification of potential fishing zones. Furthermore, the prediction of potential fishing zones relies significantly on the effectiveness of classification algorithms. Previous research has assessed the performance of models like support vector machines, naïve Bayes, and artificial neural networks (ANN). In the previous result, the results of support vector machine (SVM) were 97.6% more accurate than naive Bayes's 94.2% to classify test data for fisheries classification. By considering the recent works in this area, several recommendations for future works are presented to further improve the performance of the potential fishing zone models, which is important to the fisheries community.
Electrical signal interference minimization using appropriate core material f...IJECEIAES
As demand for smaller, quicker, and more powerful devices rises, Moore's law is strictly followed. The industry has worked hard to make little devices that boost productivity. The goal is to optimize device density. Scientists are reducing connection delays to improve circuit performance. This helped them understand three-dimensional integrated circuit (3D IC) concepts, which stack active devices and create vertical connections to diminish latency and lower interconnects. Electrical involvement is a big worry with 3D integrates circuits. Researchers have developed and tested through silicon via (TSV) and substrates to decrease electrical wave involvement. This study illustrates a novel noise coupling reduction method using several electrical involvement models. A 22% drop in electrical involvement from wave-carrying to victim TSVs introduces this new paradigm and improves system performance even at higher THz frequencies.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Bibliometric analysis highlighting the role of women in addressing climate ch...IJECEIAES
Fossil fuel consumption increased quickly, contributing to climate change
that is evident in unusual flooding and draughts, and global warming. Over
the past ten years, women's involvement in society has grown dramatically,
and they succeeded in playing a noticeable role in reducing climate change.
A bibliometric analysis of data from the last ten years has been carried out to
examine the role of women in addressing the climate change. The analysis's
findings discussed the relevant to the sustainable development goals (SDGs),
particularly SDG 7 and SDG 13. The results considered contributions made
by women in the various sectors while taking geographic dispersion into
account. The bibliometric analysis delves into topics including women's
leadership in environmental groups, their involvement in policymaking, their
contributions to sustainable development projects, and the influence of
gender diversity on attempts to mitigate climate change. This study's results
highlight how women have influenced policies and actions related to climate
change, point out areas of research deficiency and recommendations on how
to increase role of the women in addressing the climate change and
achieving sustainability. To achieve more successful results, this initiative
aims to highlight the significance of gender equality and encourage
inclusivity in climate change decision-making processes.
Voltage and frequency control of microgrid in presence of micro-turbine inter...IJECEIAES
The active and reactive load changes have a significant impact on voltage
and frequency. In this paper, in order to stabilize the microgrid (MG) against
load variations in islanding mode, the active and reactive power of all
distributed generators (DGs), including energy storage (battery), diesel
generator, and micro-turbine, are controlled. The micro-turbine generator is
connected to MG through a three-phase to three-phase matrix converter, and
the droop control method is applied for controlling the voltage and
frequency of MG. In addition, a method is introduced for voltage and
frequency control of micro-turbines in the transition state from gridconnected mode to islanding mode. A novel switching strategy of the matrix
converter is used for converting the high-frequency output voltage of the
micro-turbine to the grid-side frequency of the utility system. Moreover,
using the switching strategy, the low-order harmonics in the output current
and voltage are not produced, and consequently, the size of the output filter
would be reduced. In fact, the suggested control strategy is load-independent
and has no frequency conversion restrictions. The proposed approach for
voltage and frequency regulation demonstrates exceptional performance and
favorable response across various load alteration scenarios. The suggested
strategy is examined in several scenarios in the MG test systems, and the
simulation results are addressed.
Enhancing battery system identification: nonlinear autoregressive modeling fo...IJECEIAES
Precisely characterizing Li-ion batteries is essential for optimizing their
performance, enhancing safety, and prolonging their lifespan across various
applications, such as electric vehicles and renewable energy systems. This
article introduces an innovative nonlinear methodology for system
identification of a Li-ion battery, employing a nonlinear autoregressive with
exogenous inputs (NARX) model. The proposed approach integrates the
benefits of nonlinear modeling with the adaptability of the NARX structure,
facilitating a more comprehensive representation of the intricate
electrochemical processes within the battery. Experimental data collected
from a Li-ion battery operating under diverse scenarios are employed to
validate the effectiveness of the proposed methodology. The identified
NARX model exhibits superior accuracy in predicting the battery's behavior
compared to traditional linear models. This study underscores the
importance of accounting for nonlinearities in battery modeling, providing
insights into the intricate relationships between state-of-charge, voltage, and
current under dynamic conditions.
Smart grid deployment: from a bibliometric analysis to a surveyIJECEIAES
Smart grids are one of the last decades' innovations in electrical energy.
They bring relevant advantages compared to the traditional grid and
significant interest from the research community. Assessing the field's
evolution is essential to propose guidelines for facing new and future smart
grid challenges. In addition, knowing the main technologies involved in the
deployment of smart grids (SGs) is important to highlight possible
shortcomings that can be mitigated by developing new tools. This paper
contributes to the research trends mentioned above by focusing on two
objectives. First, a bibliometric analysis is presented to give an overview of
the current research level about smart grid deployment. Second, a survey of
the main technological approaches used for smart grid implementation and
their contributions are highlighted. To that effect, we searched the Web of
Science (WoS), and the Scopus databases. We obtained 5,663 documents
from WoS and 7,215 from Scopus on smart grid implementation or
deployment. With the extraction limitation in the Scopus database, 5,872 of
the 7,215 documents were extracted using a multi-step process. These two
datasets have been analyzed using a bibliometric tool called bibliometrix.
The main outputs are presented with some recommendations for future
research.
Use of analytical hierarchy process for selecting and prioritizing islanding ...IJECEIAES
One of the problems that are associated to power systems is islanding
condition, which must be rapidly and properly detected to prevent any
negative consequences on the system's protection, stability, and security.
This paper offers a thorough overview of several islanding detection
strategies, which are divided into two categories: classic approaches,
including local and remote approaches, and modern techniques, including
techniques based on signal processing and computational intelligence.
Additionally, each approach is compared and assessed based on several
factors, including implementation costs, non-detected zones, declining
power quality, and response times using the analytical hierarchy process
(AHP). The multi-criteria decision-making analysis shows that the overall
weight of passive methods (24.7%), active methods (7.8%), hybrid methods
(5.6%), remote methods (14.5%), signal processing-based methods (26.6%),
and computational intelligent-based methods (20.8%) based on the
comparison of all criteria together. Thus, it can be seen from the total weight
that hybrid approaches are the least suitable to be chosen, while signal
processing-based methods are the most appropriate islanding detection
method to be selected and implemented in power system with respect to the
aforementioned factors. Using Expert Choice software, the proposed
hierarchy model is studied and examined.
Enhancing of single-stage grid-connected photovoltaic system using fuzzy logi...IJECEIAES
The power generated by photovoltaic (PV) systems is influenced by
environmental factors. This variability hampers the control and utilization of
solar cells' peak output. In this study, a single-stage grid-connected PV
system is designed to enhance power quality. Our approach employs fuzzy
logic in the direct power control (DPC) of a three-phase voltage source
inverter (VSI), enabling seamless integration of the PV connected to the
grid. Additionally, a fuzzy logic-based maximum power point tracking
(MPPT) controller is adopted, which outperforms traditional methods like
incremental conductance (INC) in enhancing solar cell efficiency and
minimizing the response time. Moreover, the inverter's real-time active and
reactive power is directly managed to achieve a unity power factor (UPF).
The system's performance is assessed through MATLAB/Simulink
implementation, showing marked improvement over conventional methods,
particularly in steady-state and varying weather conditions. For solar
irradiances of 500 and 1,000 W/m2
, the results show that the proposed
method reduces the total harmonic distortion (THD) of the injected current
to the grid by approximately 46% and 38% compared to conventional
methods, respectively. Furthermore, we compare the simulation results with
IEEE standards to evaluate the system's grid compatibility.
Enhancing photovoltaic system maximum power point tracking with fuzzy logic-b...IJECEIAES
Photovoltaic systems have emerged as a promising energy resource that
caters to the future needs of society, owing to their renewable, inexhaustible,
and cost-free nature. The power output of these systems relies on solar cell
radiation and temperature. In order to mitigate the dependence on
atmospheric conditions and enhance power tracking, a conventional
approach has been improved by integrating various methods. To optimize
the generation of electricity from solar systems, the maximum power point
tracking (MPPT) technique is employed. To overcome limitations such as
steady-state voltage oscillations and improve transient response, two
traditional MPPT methods, namely fuzzy logic controller (FLC) and perturb
and observe (P&O), have been modified. This research paper aims to
simulate and validate the step size of the proposed modified P&O and FLC
techniques within the MPPT algorithm using MATLAB/Simulink for
efficient power tracking in photovoltaic systems.
Adaptive synchronous sliding control for a robot manipulator based on neural ...IJECEIAES
Robot manipulators have become important equipment in production lines, medical fields, and transportation. Improving the quality of trajectory tracking for
robot hands is always an attractive topic in the research community. This is a
challenging problem because robot manipulators are complex nonlinear systems
and are often subject to fluctuations in loads and external disturbances. This
article proposes an adaptive synchronous sliding control scheme to improve trajectory tracking performance for a robot manipulator. The proposed controller
ensures that the positions of the joints track the desired trajectory, synchronize
the errors, and significantly reduces chattering. First, the synchronous tracking
errors and synchronous sliding surfaces are presented. Second, the synchronous
tracking error dynamics are determined. Third, a robust adaptive control law is
designed,the unknown components of the model are estimated online by the neural network, and the parameters of the switching elements are selected by fuzzy
logic. The built algorithm ensures that the tracking and approximation errors
are ultimately uniformly bounded (UUB). Finally, the effectiveness of the constructed algorithm is demonstrated through simulation and experimental results.
Simulation and experimental results show that the proposed controller is effective with small synchronous tracking errors, and the chattering phenomenon is
significantly reduced.
Remote field-programmable gate array laboratory for signal acquisition and de...IJECEIAES
A remote laboratory utilizing field-programmable gate array (FPGA) technologies enhances students’ learning experience anywhere and anytime in embedded system design. Existing remote laboratories prioritize hardware access and visual feedback for observing board behavior after programming, neglecting comprehensive debugging tools to resolve errors that require internal signal acquisition. This paper proposes a novel remote embeddedsystem design approach targeting FPGA technologies that are fully interactive via a web-based platform. Our solution provides FPGA board access and debugging capabilities beyond the visual feedback provided by existing remote laboratories. We implemented a lab module that allows users to seamlessly incorporate into their FPGA design. The module minimizes hardware resource utilization while enabling the acquisition of a large number of data samples from the signal during the experiments by adaptively compressing the signal prior to data transmission. The results demonstrate an average compression ratio of 2.90 across three benchmark signals, indicating efficient signal acquisition and effective debugging and analysis. This method allows users to acquire more data samples than conventional methods. The proposed lab allows students to remotely test and debug their designs, bridging the gap between theory and practice in embedded system design.
Detecting and resolving feature envy through automated machine learning and m...IJECEIAES
Efficiently identifying and resolving code smells enhances software project quality. This paper presents a novel solution, utilizing automated machine learning (AutoML) techniques, to detect code smells and apply move method refactoring. By evaluating code metrics before and after refactoring, we assessed its impact on coupling, complexity, and cohesion. Key contributions of this research include a unique dataset for code smell classification and the development of models using AutoGluon for optimal performance. Furthermore, the study identifies the top 20 influential features in classifying feature envy, a well-known code smell, stemming from excessive reliance on external classes. We also explored how move method refactoring addresses feature envy, revealing reduced coupling and complexity, and improved cohesion, ultimately enhancing code quality. In summary, this research offers an empirical, data-driven approach, integrating AutoML and move method refactoring to optimize software project quality. Insights gained shed light on the benefits of refactoring on code quality and the significance of specific features in detecting feature envy. Future research can expand to explore additional refactoring techniques and a broader range of code metrics, advancing software engineering practices and standards.
Smart monitoring technique for solar cell systems using internet of things ba...IJECEIAES
Rapidly and remotely monitoring and receiving the solar cell systems status parameters, solar irradiance, temperature, and humidity, are critical issues in enhancement their efficiency. Hence, in the present article an improved smart prototype of internet of things (IoT) technique based on embedded system through NodeMCU ESP8266 (ESP-12E) was carried out experimentally. Three different regions at Egypt; Luxor, Cairo, and El-Beheira cities were chosen to study their solar irradiance profile, temperature, and humidity by the proposed IoT system. The monitoring data of solar irradiance, temperature, and humidity were live visualized directly by Ubidots through hypertext transfer protocol (HTTP) protocol. The measured solar power radiation in Luxor, Cairo, and El-Beheira ranged between 216-1000, 245-958, and 187-692 W/m 2 respectively during the solar day. The accuracy and rapidity of obtaining monitoring results using the proposed IoT system made it a strong candidate for application in monitoring solar cell systems. On the other hand, the obtained solar power radiation results of the three considered regions strongly candidate Luxor and Cairo as suitable places to build up a solar cells system station rather than El-Beheira.
Developing a smart system for infant incubators using the internet of things ...IJECEIAES
This research is developing an incubator system that integrates the internet of things and artificial intelligence to improve care for premature babies. The system workflow starts with sensors that collect data from the incubator. Then, the data is sent in real-time to the internet of things (IoT) broker eclipse mosquito using the message queue telemetry transport (MQTT) protocol version 5.0. After that, the data is stored in a database for analysis using the long short-term memory network (LSTM) method and displayed in a web application using an application programming interface (API) service. Furthermore, the experimental results produce as many as 2,880 rows of data stored in the database. The correlation coefficient between the target attribute and other attributes ranges from 0.23 to 0.48. Next, several experiments were conducted to evaluate the model-predicted value on the test data. The best results are obtained using a two-layer LSTM configuration model, each with 60 neurons and a lookback setting 6. This model produces an R 2 value of 0.934, with a root mean square error (RMSE) value of 0.015 and a mean absolute error (MAE) of 0.008. In addition, the R 2 value was also evaluated for each attribute used as input, with a result of values between 0.590 and 0.845.
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Sinan KOZAK
Sinan from the Delivery Hero mobile infrastructure engineering team shares a deep dive into performance acceleration with Gradle build cache optimizations. Sinan shares their journey into solving complex build-cache problems that affect Gradle builds. By understanding the challenges and solutions found in our journey, we aim to demonstrate the possibilities for faster builds. The case study reveals how overlapping outputs and cache misconfigurations led to significant increases in build times, especially as the project scaled up with numerous modules using Paparazzi tests. The journey from diagnosing to defeating cache issues offers invaluable lessons on maintaining cache integrity without sacrificing functionality.
International Conference on NLP, Artificial Intelligence, Machine Learning an...gerogepatton
International Conference on NLP, Artificial Intelligence, Machine Learning and Applications (NLAIM 2024) offers a premier global platform for exchanging insights and findings in the theory, methodology, and applications of NLP, Artificial Intelligence, Machine Learning, and their applications. The conference seeks substantial contributions across all key domains of NLP, Artificial Intelligence, Machine Learning, and their practical applications, aiming to foster both theoretical advancements and real-world implementations. With a focus on facilitating collaboration between researchers and practitioners from academia and industry, the conference serves as a nexus for sharing the latest developments in the field.
Null Bangalore | Pentesters Approach to AWS IAMDivyanshu
#Abstract:
- Learn more about the real-world methods for auditing AWS IAM (Identity and Access Management) as a pentester. So let us proceed with a brief discussion of IAM as well as some typical misconfigurations and their potential exploits in order to reinforce the understanding of IAM security best practices.
- Gain actionable insights into AWS IAM policies and roles, using hands on approach.
#Prerequisites:
- Basic understanding of AWS services and architecture
- Familiarity with cloud security concepts
- Experience using the AWS Management Console or AWS CLI.
- For hands on lab create account on [killercoda.com](https://killercoda.com/cloudsecurity-scenario/)
# Scenario Covered:
- Basics of IAM in AWS
- Implementing IAM Policies with Least Privilege to Manage S3 Bucket
- Objective: Create an S3 bucket with least privilege IAM policy and validate access.
- Steps:
- Create S3 bucket.
- Attach least privilege policy to IAM user.
- Validate access.
- Exploiting IAM PassRole Misconfiguration
-Allows a user to pass a specific IAM role to an AWS service (ec2), typically used for service access delegation. Then exploit PassRole Misconfiguration granting unauthorized access to sensitive resources.
- Objective: Demonstrate how a PassRole misconfiguration can grant unauthorized access.
- Steps:
- Allow user to pass IAM role to EC2.
- Exploit misconfiguration for unauthorized access.
- Access sensitive resources.
- Exploiting IAM AssumeRole Misconfiguration with Overly Permissive Role
- An overly permissive IAM role configuration can lead to privilege escalation by creating a role with administrative privileges and allow a user to assume this role.
- Objective: Show how overly permissive IAM roles can lead to privilege escalation.
- Steps:
- Create role with administrative privileges.
- Allow user to assume the role.
- Perform administrative actions.
- Differentiation between PassRole vs AssumeRole
Try at [killercoda.com](https://killercoda.com/cloudsecurity-scenario/)
artificial intelligence and data science contents.pptxGauravCar
What is artificial intelligence? Artificial intelligence is the ability of a computer or computer-controlled robot to perform tasks that are commonly associated with the intellectual processes characteristic of humans, such as the ability to reason.
› ...
Artificial intelligence (AI) | Definitio
Batteries -Introduction – Types of Batteries – discharging and charging of battery - characteristics of battery –battery rating- various tests on battery- – Primary battery: silver button cell- Secondary battery :Ni-Cd battery-modern battery: lithium ion battery-maintenance of batteries-choices of batteries for electric vehicle applications.
Fuel Cells: Introduction- importance and classification of fuel cells - description, principle, components, applications of fuel cells: H2-O2 fuel cell, alkaline fuel cell, molten carbonate fuel cell and direct methanol fuel cells.
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTjpsjournal1
The rivalry between prominent international actors for dominance over Central Asia's hydrocarbon
reserves and the ancient silk trade route, along with China's diplomatic endeavours in the area, has been
referred to as the "New Great Game." This research centres on the power struggle, considering
geopolitical, geostrategic, and geoeconomic variables. Topics including trade, political hegemony, oil
politics, and conventional and nontraditional security are all explored and explained by the researcher.
Using Mackinder's Heartland, Spykman Rimland, and Hegemonic Stability theories, examines China's role
in Central Asia. This study adheres to the empirical epistemological method and has taken care of
objectivity. This study analyze primary and secondary research documents critically to elaborate role of
china’s geo economic outreach in central Asian countries and its future prospect. China is thriving in trade,
pipeline politics, and winning states, according to this study, thanks to important instruments like the
Shanghai Cooperation Organisation and the Belt and Road Economic Initiative. According to this study,
China is seeing significant success in commerce, pipeline politics, and gaining influence on other
governments. This success may be attributed to the effective utilisation of key tools such as the Shanghai
Cooperation Organisation and the Belt and Road Economic Initiative.
Introduction to AI Safety (public presentation).pptx
An efficient security framework for intrusion detection and prevention in internet-of-things using machine learning technique
1. International Journal of Electrical and Computer Engineering (IJECE)
Vol. 14, No. 2, April 2024, pp. 2313~2321
ISSN: 2088-8708, DOI: 10.11591/ijece.v14i2.pp2313-2321 2313
Journal homepage: http://ijece.iaescore.com
An efficient security framework for intrusion detection and
prevention in internet-of-things using machine learning
technique
Tejashwini Nagaraj1
, Rajani Kallhalli Channarayappa2
1
Department of Computer Science and Engineering, Sai Vidya Institute of Technology, Bangalore, India
2
Department of Artificial Intelligence and Machine Learning, Cambridge Institute of Technology, Bangalore, India
Article Info ABSTRACT
Article history:
Received Mar 6, 2023
Revised Nov 27, 2023
Accepted Dec 15, 2023
Over the past few years, the internet of things (IoT) has advanced to connect
billions of smart devices to improve quality of life. However, anomalies or
malicious intrusions pose several security loopholes, leading to performance
degradation and threat to data security in IoT operations. Thereby, IoT
security systems must keep an eye on and restrict unwanted events from
occurring in the IoT network. Recently, various technical solutions based on
machine learning (ML) models have been derived towards identifying and
restricting unwanted events in IoT. However, most ML-based approaches
are prone to miss-classification due to inappropriate feature selection.
Additionally, most ML approaches applied to intrusion detection and
prevention consider supervised learning, which requires a large amount of
labeled data to be trained. Consequently, such complex datasets are
impossible to source in a large network like IoT. To address this problem,
this proposed study introduces an efficient learning mechanism to strengthen
the IoT security aspects. The proposed algorithm incorporates supervised
and unsupervised approaches to improve the learning models for intrusion
detection and mitigation. Compared with the related works, the experimental
outcome shows that the model performs well in a benchmark dataset. It
accomplishes an improved detection accuracy of approximately 99.21%.
Keywords:
Clustering techniques
Internet of things
Intrusion detection
Network security
Supervised learning
This is an open access article under the CC BY-SA license.
Corresponding Author:
Tejashwini Nagaraj
Department of Computer Science and Engineering, Sai Vidya Institute of Technology
Bangalore, Karnataka 560064, India
Email: tejashwini.n@gmail.com
1. INTRODUCTION
The idea of internet of things (IoT) has evolved with a vision to advance the technological paradigm
towards connecting numerous devices or smart objects to make our daily life more convenient and well-
organized [1]. The core operations associated with IoT involve devices that sense the environment and collect
data which is further forwarded to the respective location with technology-driven services [2], [3]. The recent
publications on IoT demonstrate its initial implications, which were limited to only small offices and homes.
However, its extended broad range spectrum can now be integrated into industries for more reliable and
smart operations, saving significant time and cost [4]. The tremendous growth of IoT devices will also make
a technological shift soon, where the possibilities of unknown cyber-attacks increase. This situation is
becoming challenging and will continue to increase with network heterogeneity. In this regard, a wide range
of research-based strategic solutions has been proposed in the past that could address the cyber-security
loopholes and protect and verify the information flow within the network. The prime motive was laid on the
2. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2313-2321
2314
basis of protecting the information confidentiality and make the system sustainable and robust to different
forms of threats and unauthorized access [5], [6]. This way, the concern rises gradually for IoT security. A
considerable effort is being emphasized to protect the data traffic from IoT cyber-attacks, which could be in
known/unknown forms. Thereby, the need to provide effective security modules arises that can detect attacks
early and restore network operations to normal at the earliest. The heterogeneity of different IoT devices and
user requirements also poses the problem of implementing cross-device security solutions in IoT, where the
traditional intrusion detection models fail to provide a full-proof defense.
Recently, machine learning (ML) based intrusion detection approaches gained much popularity
owing to their potential advantages in resisting several security threats in IoT, where distributed denial-of-
services (DDoS) is one of the most hazardous threats in the IoT network environment [7]–[9]. ML-based
approaches have a much broader scope toward effectively identifying intrusions, which is crucial in IoT
security monitoring and traffic management. An ML-based approach from the security point of view can
learn about the intrinsic details regarding threats. It can have the capability to identify even very minute
mutations in the data traffic of IoT operations [10], [11]. This introduces the realization that an appropriate
ML model can be designed, which could accomplish better attack detection accuracy and ensure lower
execution time for identification in IoT.
The relevant literature on ML-based intrusion detection and mitigation strategies are discussed as
follows: recently, Alharbi et al. [12] introduced a novel security system that targets to identify malware
threats in IoT network environment. The prime motive of this approach was to protect the IoT systems
against any form of cyber-attacks. The system has been mechanized in a way that is operated on top of the
fog-computing architecture. The presented system leverages the potential of a virtual private network (VPN)
to safeguard the communication channel with a novel security approach of challenge-response authentication.
The study outcome demonstrates the system's effectiveness with a proof-of-concept prototype and shows
experimental results to justify the performance metric. The experiment's outcome also shows that the system
is highly robust against identifying malicious attacks with low response time and consumes minimal network
resources. A similar study by Tian et al. [13] also introduces a deep learning-based security system to protect
IoT edge devices from web attacks. The study formulates web-attack detection systems that consider the
advantages of uniform resource locator (URLs). Multiple concurrent deep models are incorporated to make
the system more consistent in detecting edge-device web attacks. The outcome of the system shows that it
accomplishes a 98.91% true positive rate (TPR) and 99.410% accuracy, which makes it competitive in the
direction of intrusion detection.
The adoption of ML models has been widely employed in the detection of cyber-attacks in IoT
network environments, as seen in the studies of Ventura et al. [14], Xue et al. [15], and Alsheikh et al. [16].
These authors have suggested one thing in common IoT traffic identification is crucial in IoT security
management. These studies also claimed that the extraction of significant feature sets plays a crucial role in
accurate threat identification extraction results. Effective features indicate appropriate information to be fed
to the ML technique. These effective feature sets include both training and testing sets.
Koroniotis et al. [17] introduced a new dataset named Bot-IoT. The study formulates a system to
assess the legitimate and simulated IoT network traffic based on the new dataset and various attacks. The
authors formulate a realistic test-bed ecosystem to identify the limitations of the existing approaches in
capturing the complete vital network information. It also highlights the need for precise data labelling and
analysis of complex attack diversity so that understanding the unknown and unknown forms of attacks in the
IoT ecosystem could be easier. The study further evaluated the reliability factors associated with the Bot-IoT
data set. In this regard, the system applies several statistical and ML methods for forensics, and the validity is
further compared with the benchmark datasets. Shafiq and Yu [18] also emphasizes accurate traffic
classification problems at early stages for IoT-based 5G network applications. The authors have encouraged
the ML models toward accurate and timely Internet traffic classification. The study evaluated ten different
prominent ML algorithms using the crossover classification method. It applied two statistical analysis tests,
such as Friedman and Wilcoxon pairwise tests, to compute the results of experiments. The study outcome
exhibited the effectiveness of the random forest ML classifier for early stage and accurate classification of
internet traffic. The study by Shafiq et al. [19] also introduces a network traffic classification technique
considering the ML approaches for IoT. On the other hand, another study by Shafiq et al. [20] emphasizes
appropriate feature selection problems [21]–[23] from the IoT network dataset. The study introduces a
wrapper-based feature selection mechanism for identifying network intrusion from malicious IoT traffic. The
other related studies by the authors in [24]–[27] also talk about the need for IoT security and the implications
of ML approaches toward accurately identifying network threats. The critical review of literature clearly
outlines that the matter of fact that: i) existing ML approaches are mostly based on supervised learning,
where labeling the big dataset generated from the complex IoT network is a laborious task and also prone to
human error; ii) the unsupervised ML approaches also do not ensure better intrusion detection accuracy and
3. Int J Elec & Comp Eng ISSN: 2088-8708
An efficient security framework for intrusion detection and prevention in … (Tejashwini Nagaraj)
2315
have a track record of degrading the performance of IoT operations; iii) in the existing studies, most ML-
based approaches incorporate deep learning, which generates computational overhead to the systems of fog
nodes associated with IoT, restricting the timely response for attack/intrusion detection. The accurate
identification of intrusion within a shorter time can control the malicious event from propagating severe
consequences; iv) most of the existing intrusion detection system in IoT mostly overlooks the problem of
appropriate feature exploration and selection paradigm leading to misclassification and a higher false alarm
rate for malicious intrusion detection and v) existing system has reported very less focus towards intrusion
prevention strategies even though the focus is more towards intrusion detection. These factors motivated the
study to design a suitable simplistic ML approach for intrusion detection and mitigation in IoT. The system's
strategic design contributes to developing a methodology that solely focuses on lowering attack detection
time with enhanced accuracy levels. It introduces a semi-supervised learning-based strategic model which
could address the potential limitations of both supervised and unsupervised learning models and provide
improved detection accuracy with timely execution.
The contribution of the study is as follows: i) the study contributes towards developing a simplified
computational framework of ML which can ensure considerable intrusion detection time with accurate
identification metrics; ii) it also addresses the research challenges to avoid the pitfalls associated with the
existing supervised ML approaches and attempts to improve the accuracy of intrusion detection; iii) the
proposed system also contributes towards designing unsupervised clustering techniques that strengthen IoT
data transmission's security aspects; iv) the evaluation of the proposed methodology is performed under the
simulation considering IoT-fog devices where the robustness is checked for validating its real-time working
prospects and v) the system performance shows effectiveness under the benchmark dataset of network
security layer-knowledge discovery in database (NSL-KDD), and the experimental outcome shows that the
study not only accomplishes improved detection accuracy but also ensures lower testing time. It makes sure
of the system’s applicability to delay-sensitive use-cases. The next section discusses about adopted method of
proposed study.
2. METHOD
The prime aim of the proposed system is to leverage the enhanced working operations of semi-
supervised learning modeling toward effective intrusion detection in the IoT ecosystem. The proposed study
designs and mechanizes the algorithms deployed on the fog devices between IoT-network and cloud layers.
The study also addresses the data overfitting problem of the NSL-KDD dataset [28], which is less likely to be
explored in the existing system. The system design modeling executes three distinct modules simultaneously.
The modules are: i) data collection functional unit (DCFU); ii) semi-supervised training unit (SSTU) and
iii) intrusion detection and mitigation strategy (IDMS). The following Figure 1 shows the overview of the
IoT-fog network.
Figure 1. IoT-fog network in the proposed system formulation
4. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2313-2321
2316
According to Figure 1, a comprehensive network of end-point nodes, gateway nodes, and core
network is exhibited where IDMS algorithm is exhibited to be implemented in gateway nodes. Further, the
proposed SSTU unit combines the strengths associated with supervised and unsupervised learning paradigms.
Apart from this agenda of proposed scheme, the security functionality is targeted to be deployed to the fog-
node (FN) by offloading paradigm.
2.1. Data collection functional unit
This functional unit design basically considers the FN as a gateway for the IoT network. The data-
traffic basically flows through foreground (FG) prior reaching to the server unit (SU) in IoT. The study
formulates the proposed methodology in such a way where the DCFU unit initially verifies the incoming
traffic flow and incorporates a rule-based authentication mechanism to check the authenticity of the packets.
This entire operation takes place in the fog-node as highlighted in the Figure 1. In case the system finds that
the traffic flow does not obey the rules then the packet is further dropped as per the action taken by the
DCFU unit. The NSL-KDD dataset consists of 22 statistical attributes which are obtained from the IoT
traffic. The features could also provide better insight towards identifying unknown forms of intrusion in IoT.
The data collection phase basically considers the incoming flow of traffic 𝐼𝑇𝑟𝑎𝑓𝑓𝑖𝑐 and further extracts the
essential features 𝐸𝑓𝑒𝑡. The proposed modeling of data collection further checks the internet protocol (IP)
address of the fog-node as IP←FNi and also checks the IoT device IP which attempts to connect the FN. The
rule-based mechanism further verifies the 𝐼𝑇𝑟𝑎𝑓𝑓𝑖𝑐. For each 𝑖 ∈ 𝐼𝑜𝑇 , the system assigns the 𝐹𝑁𝐼𝑃 to the
gateway device (𝐺). Further the DCFU unit checks the ITraffic under the rule-based traffic validation
mechanism (RTV) and if the action indicates the Flag-1 then the system drops the packet, else it further
performs essential feature extraction 𝐸𝑓𝑒𝑡 with imitating.
2.2. Feature modeling
Incase if the traffic validation is successful then the system computes the essential features of traffic
with imitating. The essential features include i) size of the packet and ii) packet count. These attributes are
essential for the detection of intrusion from the IoT traffic flow. The study contributes towards the dataset
where the details of the features associated with critical IoT attacks are also considered. The extracted
imitating packets from the 𝐼𝑇𝑟𝑎𝑓𝑓𝑖𝑐 further undergoes through a pre-processing mechanism for the effective
data-cleaning operations. The proposed system considers a set of feature attributes which are appropriately
selected from the incoming traffic which are-count of the packet, link estimation for used bandwidth,
standard deviation, average, weighted moving average, magnitude, radius, covariance, correlation factor,
entropy estimation, and information distance computation.
2.3. Semi-supervised training unit
The proposed system designs the concept of semi-supervised unit considering the potential features
of deep neural networks (DNN). The study mechanizes the learning function of SSTU in such a way where it
combines the DNN potential features with K-means clustering mechanism. However, the single layer feed-
forward neural network is not suitable for providing ample information on the size of the network despite its
capability of providing higher accuracy in classification problems. The algorithm for SSTU unit is provided
in Algorithm 1.
This has been justified by the universal approximation theorem [29]. This limitation is addressed in
the proposed system by studying the properties of deep feed forward neural network (DFNN) not only
reduces the generalization error but also verify the count of the nodes in the hidden units. The proposed study
introduces a customized function fDFNN(x) that considers the size of the network for training and also aims to
reduce the generalization error with web of interconnected neurons across several hidden layers. Here the
neurons non-linear characteristics basically helps the model to understand the pattern of attack from the data
traffic with adjustments in input-output combinations. The limitations associated with the DFNN is also
addressed in the proposed study and it is observed that DFNN all alone cannot be robust against new form of
attack strategy and in that case, it will not be able to predict the attack with higher level of accuracy. The
SSTU component further also introduces another customized functional module fDFNN(x) of enhanced K-
means clustering which when combined with the enhanced DFNN provides significant outcome. The study
considers the strength factors of K-means clustering approach which have enough capability to appropriately
classify the unknown traffic data. The function fDFNN(x) basically runs on the top of proposed fDFNN(x).
Initially the DFNN dataset is labeled and the intermediate training model is prepared. Further the trained
model of fDFNN(x) divide the classes into a set of classes such as 𝐷𝐶 ← {𝐴𝐶1, 𝐴𝐶2, ⋯ 𝐴𝐶𝑗 ⋯ 𝑁𝐶}. Here DC
represents the divided class whereas AC represent attack classes and NC refers to normal class. Here the role
of the supervised DFNN model is it provides nearly perfect initial data points to the K-means for clustering
5. Int J Elec & Comp Eng ISSN: 2088-8708
An efficient security framework for intrusion detection and prevention in … (Tejashwini Nagaraj)
2317
which improves the accuracy of attack identification. The proposed K-means clustering further computes the
random samples of attack classes and computes Euclidian distance between and points considering the
unlabeled dataset and further classify the adversarial cluster unit and normal cluster unit which is further
again forwarded to the trained model.
The algorithm design and modeling are numerically performed and it clearly shows that from step-1
to step-18 has already been covered up in the above segment of the study. However, the further portion of the
algorithm activates the proposed clustering mechanism of fDFNN(x) which considers the training model-1
Tmodel1 which is computed from the ƒ𝐷𝐹𝑁𝑁(𝑥) computation. The algorithm further optimizes the process of
computation of predictor classes and also performs the clustering of training data (TD). The function further
also approzimate the random samples 𝑅𝑁(𝑖) which are further assigned to each of the clusters. It also
incorporates unlabeled training data 𝑢𝐿_𝑇𝐷(𝑖) and assign the datapoints into the clusters and compute the
Euclidian distance 𝐸𝐷(𝑅𝑁 − 𝑇𝐷) between the samples and the training data. Further the proposed method
also introduces a thresholding mechanism (𝑇) which assists in finding the appropriate cluster for intrusion
criticality analysis. Finally, the SSTU system returns the trained model to the output.
Algorithm 1. Proposed semi-supervised learning model
Input: ITraffic
Output: Trained Model Tmodel2
Begin
IP←FNi
For each i ∈ IoT
Assign FNIP → G
End
Employ (RTV)
IF (ITraffic against RTV)
Drop(packet)
Else
Extract(Efet)
Enable: ƒDFNN(x):pass in Efet
DC ← {AC1, AC2, ⋯ ACj ⋯ NC}
Labeling of training data (TD) of n samples
Init: layers, neurons, bias, weight, learning rate, epoch, accuracy
Compute: accuracy ← #(actual == observed)/n × 100
If (accuracy is not satisfactory)
change training attributes
Else
return→ trained model Tmodel1
Enable: ƒKmeans(x): pass in: Tmodel1
Compute predictor classes
Perform clustering of TD
Random samples of 𝑅𝑁(𝑖) ← 𝐶𝑖
Add uL_TD(i) → 𝐶𝑖 , 𝐸𝐷(𝑅𝑁 − 𝑇𝐷)
Thresholding (T)
Final 𝐶𝑖
Return Trained Model Tmodel2
End
2.4. Proposed intrusion detection and mitigation strategy
The proposed intrusion detection strategy basically takes the input of 𝐸𝑓𝑒𝑡 and with the feature it
trains the model 𝑇𝑚𝑜𝑑𝑒𝑙2 and computes the intrusion status. If the intrusion is found to be normal then the
IDMS module continues the normal IoT operations. If the intrusion is of known class, then it generates the
status accordingly. If incase the intrusion is found to be of unknown form then the IDMS system generates
alert. The IDMS unit further also functionalizes intrusion mitigation strategy where it considers the
assessment of attack status. If the intrusion is found to be of unknown class, then the IDMS system enables
drop rules to the media access control internet protocol (MAC_IP) from FN. Here the MAC_IP belongs to
the intruder IoT node that has transmitted the malicious packets. The drop rule is set considering a defined
random time-stamp. Once the random time stamp expires then the drop rule is revoked from the ruleset. Here
the time stamp remains unknown so that intruder cannot properly understand the time-strategy. If the
intrusion is found to be of unknown form, then the IDMS system also employ the drop-rule but for limited
random time-stamp. Here the time-stamp is set to small random timer as IDMS is not sure about the type of
intrusion. In that case the IDMS system also verifies the traffic behavior if it is found suspicious then again
drop-rule is set. Else no rule is set. Further the system updates the traffic instances with new observed data.
The next section further illustrates the experimental results obtained from simulating the proposed algorithm
in a simulation environmental testbed.
6. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2313-2321
2318
3. RESULTS AND DISCUSSION
In this section, the results obtained from the simulation of the presented approach is demonstrated.
The study considers a simulation testbed of IoT-fog cloud [30] to evaluate the performance of the proposed
system. The fog-node is configured with a component of Cisco Nexus switch device of 5672UP. It considers
Cisco NX-OS operating system with other programmable features. The cloud comprises of Quadcore Intel
CPU E5620 @2.40 GHz and Xen PVM hypervisor. The simulation testbed also considers total 30 IoT nodes
which are connected with the Raspberry Pi connected to various sensor nodes. The Raspberry Pi consists of
1.2 GHz 64-bit quad-core ARMv8 processor with 1 GB RAM size and Strech OS with 64 GB memory. The
Fog-Node is programmable in the proposed study where the rule-based mechanism can be employed for
mitigating the attacks considering the traffic assessment. The optimal training parameter values in the
proposed system for the training of SSTU which are shown with the following Table 1.
Table 1. SSTU optimal training parameters
Serial number Parameter Optimal value
1 Hidden layer count 7-8
2 Neuron count 100-200
3 Activation function Sigmoid
4 Learning rate 0.04-0.06
5 No of epoch 700-900
In the proposed system a total number of approximately 120,000 tuples are generated from the
traffic dataset of NSL-KDD, where a total of 11,530 tuples are labeled for initial input of training. The
performance metric to evaluate the effectiveness of the proposed system considers a set of parameters which
are accuracy of intrusion detection, detection rate and response time of detection. The metric accuracy
indicates the percentage of correctly identified network intrusion from the traffic instances. It also indicates
whether the traffic is suspicious or not. The measure of accuracy in (1) is computed for the performance
evaluation of the proposed system.
Acc = (
TP+TN
TP+TN+FN+FP
) (1)
The accuracy Acc parameter computation considers the values of true positive score (TP), along
with the true negative score TN, false negative score FN and false positive score FP. In (2), the intrusion
detection rate 𝐷𝑟𝑎𝑡𝑒 is measured for the purpose of numerical evaluation. The Figure 2 shows the
comparative outcome of the proposed system towards accuracy of the intrusion detection. The comparison
has been performed with the conventional popular related approaches of intrusion detection in IoT
eco-system.
Drate = (
TP
TP+FN
) (2)
Figure 2. Comparing simulation results of detection accuracy (%)
7. Int J Elec & Comp Eng ISSN: 2088-8708
An efficient security framework for intrusion detection and prevention in … (Tejashwini Nagaraj)
2319
The proposed study considers the much popular related works of Zhang et al. [31], Diro and
Chilamkurti [32], Rathore and Park [33], and Zhao et al. [34] for the purpose of comparison and it clearly
shows that when it comes to detection accuracy the proposed SSTU outperforms the existing system by
approximately 99.72% of detection accuracy. The prime reason is that it applies the proposed semi-
supervised learning model which is trained with the appropriate features. The simulation results comparison
is illustrated in Figure 3. The Figure 3(a) and Figure 3(b) further also shows the analysis of detection rate and
detection time respectively. The outcome shows that proposed scheme adopting semi-supervised learning
methods excels better performance in contrast to existing studies. Proposed scheme achieves 99.81% of
accurate in detection rate that is higher enough to facilitate better resistivity towards various threats. Further,
it is also seen that work carried out by [31], [34] attains comparable outcome owing to the adoption of neural
network.
(a)
(b)
Figure 3. Comparing simulation results for (a) intrusion detection rate and (b) detection time (s)
In the context of detection time analysis, it is quite clear that the approach of [33] attains better
detection time but it comes with a cost of lsser detection accuracy which is approximately 94.61%. However,
the proposed system of semi-supervised learning improvises the detection time to 1895.21 which is quite
superior and balanced in comparison to supervised learning models. Hence, the proposed system attains a
balanced outcome towards identifying the network intrusions in IoT and also contributes to the security
functionalities in fog-computing.
8. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 14, No. 2, April 2024: 2313-2321
2320
4. CONCLUSION
The study introduces a novel security framework of intrusion detection and prevention system for
IoT-network operations. It realizes the advantages and popularity of ML techniques towards identifying the
network intrusion from the traffic flows that pass-through fog-nodes inside the IoT eco-system. However, the
study also addresses the pitfalls associated with the supervised and unsupervised learning approaches towards
improving the accuracy of attack detection. The prime reason came out to be the inappropriateness in feature
selection and also the problem of exhaustive network data labeling in supervised learning models.
Addressing the potential research problems in existing system. The proposed study introduces a novel SSTU
learning framework that functionalize the deep learning on the top of K-means clustering approach towards
identifying the network intrusions in IoT. The proposed study also contributes towards feature labeling
considering the NSL-KDD dataset. This approach of appropriate feature selection has enhanced the learning
accuracy which have resulted in better intrusion detection and prevention considering huge network traffic.
The contribution of the study are as follows: i) unlike related works the proposed system simplifies the
design of semi-supervised learning where it also contributes towards feature selection; ii) the proposed study
outcome yields a balanced performance between attack detection accuracy and detection time which is still a
missing gap and research challenge in the existing research trend; iii) the proposed study also contributes
towards identifying unknown forms of adversaries in the IoT-network whereas in the existing system
majority of the approaches are specific towards particular form of attacks and iv) unlike existing system it
also introduces attack prevention strategy and also outperforms the existing system in attack detection
accuracy which approximately 99.72%. The future research work will be carried out towards optimizing the
outcome of computational time complexity of the proposed SSTU-approach. It also furthers targets to
optimize the learning parameters of SSTU approach so that accuracy of attack detection should be improved
to more extent.
REFERENCES
[1] J. Qiu, Z. Tian, C. Du, Q. Zuo, S. Su, and B. Fang, “A survey on access control in the age of internet of things,” IEEE Internet of
Things Journal, vol. 7, no. 6, pp. 4682–4696, Jun. 2020, doi: 10.1109/JIOT.2020.2969326.
[2] Y. N. Soe, Y. Feng, P. I. Santosa, R. Hartanto, and K. Sakurai, “Implementing lightweight IoT-IDS on raspberry pi using
correlation based feature selection and its performance evaluation,” in in International Conference on Advanced Information
Networking and Applications, Springer, 2020, pp. 458–469, doi: 10.1007/978-3-030-15032-7_39.
[3] A. Hamdan, B. Alareeni, R. Hamdan, and M. A. Dahlan, “Incorporation of artificial intelligence, big data, and internet of things
(IoT): an insight into the technological implementations in business success,” Journal of Decision Systems, pp. 1–4, Nov. 2022,
doi: 10.1080/12460125.2022.2143618.
[4] J. Qiu, L. Du, D. Zhang, S. Su, and Z. Tian, “Nei-TTE: intelligent traffic time estimation based on fine-grained time derivation of
road segments for smart city,” IEEE Transactions on Industrial Informatics, vol. 16, no. 4, pp. 2659–2666, Apr. 2020, doi:
10.1109/TII.2019.2943906.
[5] F. Schuster and A. Habibipour, “Users’ privacy and security concerns that affect IoT adoption in the home domain,” International
Journal of Human–Computer Interaction, pp. 1–12, Nov. 2022, doi: 10.1080/10447318.2022.2147302.
[6] D. E. Denning, “An intrusion-detection model,” IEEE Transactions on Software Engineering, vol. SE-13, no. 2, pp. 222–232,
Feb. 1987, doi: 10.1109/TSE.1987.232894.
[7] X. Du, M. Guizani, Y. Xiao, and H.-H. Chen, “Defending DoS attacks on broadcast authentication in wireless sensor networks,”
in 2008 IEEE International Conference on Communications, 2008, pp. 1653–1657, doi: 10.1109/ICC.2008.319.
[8] L. Wu, X. Du, W. Wang, and B. Lin, “An out-of-band authentication scheme for internet of things using blockchain technology,”
in 2018 International Conference on Computing, Networking and Communications (ICNC), Mar. 2018, pp. 769–773, doi:
10.1109/ICCNC.2018.8390280.
[9] Z. Tian, X. Gao, S. Su, and J. Qiu, “Vcash: a novel reputation framework for identifying denial of traffic service in internet of
connected vehicles,” IEEE Internet of Things Journal, vol. 7, no. 5, pp. 3901–3909, May 2020, doi: 10.1109/JIOT.2019.2951620.
[10] S. Prabavathy, K. Sundarakantham, and S. M. Shalinie, “Design of cognitive fog computing for intrusion detection in internet of
things,” Journal of Communications and Networks, vol. 20, no. 3, pp. 291–298, Jun. 2018, doi: 10.1109/JCN.2018.000041.
[11] A. Abeshu and N. Chilamkurti, “Deep learning: the frontier for distributed attack detection in fog-to-things computing,” IEEE
Communications Magazine, vol. 56, no. 2, pp. 169–175, Feb. 2018, doi: 10.1109/MCOM.2018.1700332.
[12] S. Alharbi, P. Rodriguez, R. Maharaja, P. Iyer, N. Bose, and Z. Ye, “FOCUS: a fog computing-based security system for the
internet of things,” in 2018 15th IEEE Annual Consumer Communications & Networking Conference (CCNC), Jan. 2018, pp. 1–5,
doi: 10.1109/CCNC.2018.8319238.
[13] Z. Tian, C. Luo, J. Qiu, X. Du, and M. Guizani, “A distributed deep learning system for web attack detection on edge devices,”
IEEE Transactions on Industrial Informatics, vol. 16, no. 3, pp. 1963–1971, Mar. 2020, doi: 10.1109/TII.2019.2938778.
[14] D. Ventura, D. Casado-Mansilla, J. López-de-Armentia, P. Garaizar, D. López-de-Ipiña, and V. Catania, “ARIIMA: a real IoT
implementation of a machine-learning architecture for reducing energy consumption,” in in International Conference on
Ubiquitous Computing and Ambient Intelligence, Springer, 2014, pp. 444–451, doi: 10.1007/978-3-319-13102-3_72.
[15] R. Xue, L. Wang, and J. Chen, “Using the IoT to construct ubiquitous learning environment,” in 2011 Second International
Conference on Mechanic Automation and Control Engineering, Jul. 2011, pp. 7878–7880, doi: 10.1109/MACE.2011.5988881.
[16] M. A. Alsheikh, S. Lin, D. Niyato, and H.-P. Tan, “Machine learning in wireless sensor networks: algorithms, strategies, and
applications,” IEEE Communications Surveys & Tutorials, vol. 16, no. 4, pp. 1996–2018, 2014, doi: 10.1109/COMST.2014.2320099.
[17] N. Koroniotis, N. Moustafa, E. Sitnikova, and B. Turnbull, “Towards the development of realistic botnet dataset in the internet of
things for network forensic analytics: Bot-IoT dataset,” Future Generation Computer Systems, vol. 100, pp. 779–796, Nov. 2019,
doi: 10.1016/j.future.2019.05.041.
9. Int J Elec & Comp Eng ISSN: 2088-8708
An efficient security framework for intrusion detection and prevention in … (Tejashwini Nagaraj)
2321
[18] M. Shafiq and X. Yu, “Effective packet number for 5G IM wechat application at early stage traffic classification,” Mobile
Information Systems, vol. 2017, pp. 1–22, 2017, doi: 10.1155/2017/3146868.
[19] M. Shafiq, X. Yu, A. A. Laghari, L. Yao, N. K. Karn, and F. Abdessamia, “Network traffic classification techniques and
comparative analysis using machine learning algorithms,” in 2016 2nd IEEE International Conference on Computer and
Communications (ICCC), Oct. 2016, pp. 2451–2455, doi: 10.1109/CompComm.2016.7925139.
[20] M. Shafiq, Z. Tian, A. K. Bashir, X. Du, and M. Guizani, “IoT malicious traffic identification using wrapper-based feature
selection mechanisms,” Computers & Security, vol. 94, p. 101863, Jul. 2020, doi: 10.1016/j.cose.2020.101863.
[21] M. Shafiq, Z. Tian, Y. Sun, X. Du, and M. Guizani, “Selection of effective machine learning algorithm and Bot-IoT attacks traffic
identification for internet of things in smart city,” Future Generation Computer Systems, vol. 107, pp. 433–442, Jun. 2020, doi:
10.1016/j.future.2020.02.017.
[22] S. Egea, A. Rego Manez, B. Carro, A. Sanchez-Esguevillas, and J. Lloret, “Intelligent IoT traffic classification using novel search
strategy for fast-based-correlation feature selection in industrial environments,” IEEE Internet of Things Journal, vol. 5, no. 3,
pp. 1616–1624, Jun. 2018, doi: 10.1109/JIOT.2017.2787959.
[23] S. Su, Y. Sun, X. Gao, J. Qiu, and Z. Tian, “A correlation-change based feature selection method for IoT equipment anomaly
detection,” Applied Sciences, vol. 9, no. 3, pp. 1–14, Jan. 2019, doi: 10.3390/app9030437.
[24] M. R. Belgaum, Z. Alansari, S. Musa, M. Mansoor Alam, and M. S. Mazliham, “Role of artificial intelligence in cloud
computing, IoT and SDN: reliability and scalability issues,” International Journal of Electrical and Computer Engineering
(IJECE), vol. 11, no. 5, pp. 4458–4470, Oct. 2021, doi: 10.11591/ijece.v11i5.pp4458-4470.
[25] D. Khwailleh and F. Al-balas, “A dynamic data encryption method based on addressing the data importance on the internet of
things,” International Journal of Electrical and Computer Engineering (IJECE), vol. 12, no. 2, pp. 2139–2146, Apr. 2022, doi:
10.11591/ijece.v12i2.pp2139-2146.
[26] H. A. Khan, R. Abdulla, S. K. Selvaperumal, and A. Bathich, “IoT based on secure personal healthcare using RFID technology
and steganography,” International Journal of Electrical and Computer Engineering (IJECE), vol. 11, no. 4, pp. 3300–3309, Aug.
2021, doi: 10.11591/ijece.v11i4.pp3300-3309.
[27] R. Zhao et al., “A novel intrusion detection method based on lightweight neural network for internet of things,” IEEE Internet of
Things Journal, vol. 9, no. 12, pp. 9960–9972, Jun. 2022, doi: 10.1109/JIOT.2021.3119055.
[28] A. Shiravani, M. H. Sadreddini, and H. N. Nahook, “Network intrusion detection using data dimensions reduction techniques,”
Journal of Big Data, vol. 10, no. 1, pp. 1–25, Mar. 2023, doi: 10.1186/s40537-023-00697-5.
[29] M.-X. Wang and Y. Qu, “Approximation capabilities of neural networks on unbounded domains,” Neural Networks, vol. 145,
pp. 56–67, Jan. 2022, doi: 10.1016/j.neunet.2021.10.001.
[30] N. Ravi and M. S. Selvaraj, “TeFENS: testbed for experimenting next-generation-network security,” in 2018 IEEE 5G World
Forum (5GWF), Jul. 2018, pp. 204–209, doi: 10.1109/5GWF.2018.8516708.
[31] Y. Zhang, P. Li, and X. Wang, “Intrusion detection for IoT based on improved genetic algorithm and deep belief network,” IEEE
Access, vol. 7, pp. 31711–31722, 2019, doi: 10.1109/ACCESS.2019.2903723.
[32] A. A. Diro and N. Chilamkurti, “Distributed attack detection scheme using deep learning approach for internet of things,” Future
Generation Computer Systems, vol. 82, pp. 761–768, May 2018, doi: 10.1016/j.future.2017.08.043.
[33] S. Rathore and J. H. Park, “Semi-supervised learning based distributed attack detection framework for IoT,” Applied Soft
Computing, vol. 72, pp. 79–89, Nov. 2018, doi: 10.1016/j.asoc.2018.05.049.
[34] J. Li, Z. Zhao, R. Li, and H. Zhang, “AI-based two-stage intrusion detection for software defined IoT networks,” IEEE Internet of
Things Journal, vol. 6, no. 2, pp. 2093–2102, Apr. 2019, doi: 10.1109/JIOT.2018.2883344.
BIOGRAPHIES OF AUTHORS
Tejashwini Nagaraj she has completed her B.E from SVCE, Bengaluru
Karnataka and M. Tech is from Dr. AIT, Bengaluru, Karanataka, and Ph.D with research topic
“Design of energy efficient and secure algorithm for wireless environment using public key
encryption” in network security in wireless sensor networks under Visvesvaraya Technological
University in the year 2022. She is having six years of teaching and research experience in
respective engineering colleges under Visvesvaraya Technological University, Belagavi, and
Karnataka, India. Her interest includes digital image communication, wireless communication,
wireless sensor network and operating system. Currently she is pursuing her research for PhD
under Visvesvaraya Technological University, Belagavi, and Karnataka. She has published her
work in various international conferences and journals. She can be contacted at email:
tejashwini.n@gmail.com.
Rajani Kallhalli Channarayappa is the assistant professor in Department of
Artificial Intelligence and Machine Learning in the Cambridge Institute of Technology, K R
Puram, Blore at VTU, Belgaum. She completed B.E from NCET, and MTech from Atria
Institute of Technology. She submitted thesis and pursuing research work under VTU. Her
research interest focuses on mobile ad-hoc networks, wireless sensor networks, WANET’S and
machine learning. She has many publications on isolating routing misbehavior problems in
mobile ad hoc networks. She had more than 8 years of teaching experience worked as assistant
professor in various colleges like NCET, SRSIT, and Presidency University. During her career
she taught students with various subjects to students like C# programming and .net, DBMS,
OOMD, FS, SE, ST, web programming, CO, C-Programming and C++. My vision is to be to
be a successful teacher by incorporating good teaching values and to provide students a quality
in teaching. She can be contacted at email: rajanikcc009@gmail.com.