SlideShare a Scribd company logo
1 of 25
Download to read offline
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Secure Multi-Party Computation Based Privacy
Preserving Extreme Learning Machine Algorithm
Over Vertically Distributed Data
Ferhat ¨Ozg¨ur C¸atak
ozgur.catak@tubitak.gov.tr
T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute
Kocaeli, Turkey
Nov. 10 2015
The 2015 International Data Mining and Cybersecurity Workshop
With ICONIP2015
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Table of Contents
1 Introduction
Secure Multiparty Computation
Contributions
2 Preliminaries
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
3 Privacy-preserving ELM over vertically partitioned data
Privacy-preserving ELM
4 Experiments
Experimental setup
Simulation Results
5 Conclusions
Conclusions
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Secure Multiparty Computation
Contributions
Table of Contents
1 Introduction
Secure Multiparty Computation
Contributions
2 Preliminaries
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
3 Privacy-preserving ELM over vertically partitioned data
Privacy-preserving ELM
4 Experiments
Experimental setup
Simulation Results
5 Conclusions
Conclusions
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Secure Multiparty Computation
Contributions
Secure Multiparty Computation (SMC)
Definition
SMC : The goal of creating methods for parties to jointly compute
a function over their inputs while keeping those inputs private.
In an MPC,
a given number of participants, p1, p2, · · · , pN
each has private data, respectively d1, d2, · · · , dN
Participants want to compute the value of a public function on
that private data:
F(d1, d2, ..., dN ) while keeping their own inputs secret.
Challenges :
To protect each participant’s private data, and intermediate results
The computation/communication cost introduced to each
participant shall be affordable
Training data is arbitrarily partitioned
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Secure Multiparty Computation
Contributions
Contributions
Main contributions of the work
Privacy-preserving Extreme Learning Machine (ELM) training
model
Global ELM classification model from the distributed data sets in
multiple parties
Training data set is vertically partitioned among the parties
The final distributed model is constructed at an independent party
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Table of Contents
1 Introduction
Secure Multiparty Computation
Contributions
2 Preliminaries
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
3 Privacy-preserving ELM over vertically partitioned data
Privacy-preserving ELM
4 Experiments
Experimental setup
Simulation Results
5 Conclusions
Conclusions
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Extreme Learning Machine (ELM)
Learning Without Iterative Tuning
All hidden node parameters can be randomly generated without the
knowledge of the training data. That is, for any continuous target
function f and any randomly generated sequence
limL→∞ ||f (x) − fL(x)|| = limL→∞ ||f (x) −
L
i=1 βi G(ai , bi , x)|| = 0
holds with probability one if βi is chosen to minimize
||f (x) − fL(x)||, ∀i
G.-B. Huang, et al., ”Universal approximation using incremental constructive
feedforward networks with random hidden nodes,” IEEE Transactions on Neural
Networks, vol. 17, no. 4, pp. 879-892, 2006.
G.-B. Huang, et al., ”Convex incremental extreme learning machine,”
Neurocomputing, vol. 70, pp. 3056-3062, 2007.
G.-B. Huang, et al., ”Enhanced random search based incremental extreme learning
machine,” Neurocomputing, vol. 71, pp. 3460-3468, 2008.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Extreme Learning Machine (ELM)
Figure: Generalized SLFN
Mathematical Model
For N arbitrary distinct samples
(xi , ti ) ∈ Rn × Rm, SLFNs with L
hidden nodes each with output
function, G(ai , bi , x) are
mathematically modeled as
L
i=1
βi G(ai , bi , xj ) = tj , j = 1, ..., N
(1)
(ai , bi ): hidden node parameters.
βi : the weight vector connecting the
ith hidden node and the output node.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Extreme Learning Machine (ELM)
Mathematical Model
L
i=1 βi G(ai , bi , xj ) = tj , j = 1, ..., N is equivalent to Hβ = T where,



h(x1)
...
h(xN)


 =



G(a1, b1, x1) · · · G(aL, bL, x1)
...
...
...
G(a1, b1, xN) · · · G(aL, bL, xN)



N×L
(2)
β =



βT
1
...
βT
L



L×m
ve T =



tT
1
...
tT
N



N×m
(3)
H, is called the hidden layer output matrix of the neural network, the ith
column of H is the output of the ith hidden node with respect to inputs ,
x1, ..., xn
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Extreme Learning Machine (ELM)
Three-Step Learning Model
Given a training set D = {(xi , ti )|xi ∈ Rn
, ti ∈ Rm
, i = 1, · · · , N}, hidden
node output function G(a, b, x), and the number of hidden nodes L,
1 Assign randomly hidden node parameters (ai , bi ), i = 1, · · · , L.
2 Calculate the hidden layer output matrix H.
3 Calculate the output weight β = Ht
T.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Secure Multi Party Computation
Secure Multi-Party Computation
The problem of n players to compute an agreed function f of their
inputs
In vertically partitioned data, each party holds different attributes of
same data set.
The partition strategy is shown in Figure 2.
x1,1 · · · x1,t−1 · · · x1,t · · · x1,k
x2,1 · · · x2,t−1 · · · x2,t · · · x2,k
...
...
...
...
...
...
...
xm,1 · · · xm,t−1 · · · xm,t · · · xm,k














P1 · · · Pk
D =
Figure: Vertically partitioned data set D.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Secure Multi-Party Addition I
Secure Multi-Party Addition
Assume k ≥ 3 parties, P0, · · · , Pk−1, with party Pi holding value vi
Aim is to compute v =
k−1
i=0
vi
Sum of vi lies in F
P0 randomly chooses a number R ∈ F
P0 adds R to its local value v0,
Sends v0 = R + v0mod|F| to P1
The remaining parties Pi , i = 1, · · · , k − 1
Pi receives V = R +
i−1
j=0
vj mod|F|
Pi sends R + j=1
ivj mod|F| = (vi + V )mod|F|
Finally, P0, subtracts R from the final message to compute actual
results.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Secure Multi-Party Addition II
Party0
x0 , R ∈ F
Party1
x1
Party2
x2
Partyk
xk
V = R + x0mod|F|
V = R +
i−1
j=0 xjmod|F|
(xi + V )mod|F|
Figure: Secure Multi-Party Addition.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
Secure Multi-Party Addition III
Algorithm 1: Secure multi-party addition
1: procedure SMA(P)
2: P0 : R ← rand(F) P0 randomly chooses a number R
3: V ← R + x0 mod F
4: P0 sends V to node P1
5: for i = 1, · · · , k − 1 do
6: Pi receives V = R +
i−1
j=0
xj mod F
7: Pi computes V = R +
i
j=1
xj mod F = ((xi + V ) mod F)
8: Pi sends V to node Pi+1
9: P0 : V ← (V − R) = (V − R mod F) Actual addition result
10: end procedure
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Privacy-preserving ELM
Table of Contents
1 Introduction
Secure Multiparty Computation
Contributions
2 Preliminaries
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
3 Privacy-preserving ELM over vertically partitioned data
Privacy-preserving ELM
4 Experiments
Experimental setup
Simulation Results
5 Conclusions
Conclusions
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Privacy-preserving ELM
Privacy-preserving ELM I
1 Master party creates weight matrix, W ∈ RL×N
2 Master party distributes partition W with same feature size for each
parties.
3 Party P0 creates a random matrix,
R =



rand1,1(F) · · · rand1,L(F)
...
...
...
randN,1(F) · · · randN,L(F)



N×L
4 Party P0 creates perturbated output,
V = R +



x0
1 · w0
1 + b0
1 · · · x0
1 · w0
L + b0
L
...
...
...
x0
N · w0
1 + b0
1 · · · x0
N · w0
L + b0
L



5 for i = 1, · · · , k − 1
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Privacy-preserving ELM
Privacy-preserving ELM II
Pi computes V = V +



xi
1 · wi
1 + bi
1 · · · xi
1 · wi
L + bi
L
...
...
...
xi
N · wi
1 + bi
1 · · · xi
L · wi
N + bi
N



Pi sends V to Pi+1
6 P0 subtracts random matrix, R, from the received matrix V.
H = (V − R) mod F
7 Hidden layer node weight vector, β, is calculated. β = H†
· T
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Privacy-preserving ELM
Privacy-preserving ELM III
P arty0
x0
, w, H0
,R ∈ F,
Party1
x1
, H1
, w
Party2
x2
, H2
, w
Partyk
xk−1
,
Hk−1
, w
V0 = R +
H0
mod|F|
V1 = V0+H1
mod|F|
V2 = V1 + H2
mod|F|
Vk = Vk−1 + Hk
mod|F|
Hi
=




G(w1, b1, xi
1) · · · G(wL, bL, xi
1)
.
.
.
...
.
.
.
G(w1, b1, xi
N ) · · · G(wL, bL, xi
N )




N×L
R =




rand1,1(F) · · · rand1,L(F)
.
.
.
...
.
.
.
randN,1(F) · · · randN,L(F)




N×L
H = (V − R) mod F
Figure: Overview of privacy-preserving ELM learning.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Experimental setup
Simulation Results
Table of Contents
1 Introduction
Secure Multiparty Computation
Contributions
2 Preliminaries
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
3 Privacy-preserving ELM over vertically partitioned data
Privacy-preserving ELM
4 Experiments
Experimental setup
Simulation Results
5 Conclusions
Conclusions
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Experimental setup
Simulation Results
Experimental setup I
Our approach is applied to six different data sets to verify its model
effectivity and efficiency.
Table: Description of the testing data sets used in the experiments.
Data set #Train #Classes #Attributes
australian 690 2 14
colon-cancer 62 2 2,000
diabetes 768 2 8
duke breast cancer 44 2 7,129
heart 270 2 13
ionosphere 351 2 34
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Experimental setup
Simulation Results
Simulation Results I
The number of party size, k: from 3 to number of feature n, of the
data set
For instance, k = 3, and n = 14, then the first two party have 5
attributes, and last party has 4 attributes.
The accuracy of secure multi-party computation based ELM is
exactly same for the traditional ELM training algorithm.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Experimental setup
Simulation Results
Simulation Results II
Figure shows results of our simulations.
Time scale becomes its steady state position when number of parties
k, moves closer to number of attributes, n.
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
10
−1
10
0
10
1
10
2
10
3
AttributeS ize(n)
P artyS ize(k)
Timescale
australian colon−cancer diabetes duke heart ionosphere
Figure: Vertically partitioned data set D.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Conclusions
Table of Contents
1 Introduction
Secure Multiparty Computation
Contributions
2 Preliminaries
ELM
Secure Multi Party Computation
Secure Multi-Party Addition
3 Privacy-preserving ELM over vertically partitioned data
Privacy-preserving ELM
4 Experiments
Experimental setup
Simulation Results
5 Conclusions
Conclusions
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Conclusions
Conclusions
Summary
ELM learning algorithm, a new method.
ELM outperforms traditional Single Layer Feed-forward Neural-networks and
Support Vector Machines for Big Data 1
In all fields that ELM is applied (i.e. medical records, business, government),
privacy is a major concern.
Conclusions
Privacy-preserving learning model is proposed in vertically partitioned data
In multi-party partitioning without sharing the data of each site to
the others.
Master party divides weight vector, and each party calculates the activation
function result with its data and weight vector.
1Cambria, Erik, et al. ”Extreme learning machines [trends & controversies].”
Intelligent Systems, IEEE 28.6 (2013): 30-59.
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
Introduction
Preliminaries
Privacy-preserving ELM over vertically partitioned data
Experiments
Conclusions
Conclusions
Thank You
Ferhat ¨Ozg¨ur C¸atak
ozgur.catak@tubitak.gov.tr
Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin

More Related Content

What's hot

Developing Document Image Retrieval System
Developing Document Image Retrieval SystemDeveloping Document Image Retrieval System
Developing Document Image Retrieval SystemKonstantinos Zagoris
 
Unsupervised Feature Learning
Unsupervised Feature LearningUnsupervised Feature Learning
Unsupervised Feature LearningAmgad Muhammad
 
Dynamic Two-Stage Image Retrieval from Large Multimodal Databases
Dynamic Two-Stage Image Retrieval from Large Multimodal DatabasesDynamic Two-Stage Image Retrieval from Large Multimodal Databases
Dynamic Two-Stage Image Retrieval from Large Multimodal DatabasesKonstantinos Zagoris
 
PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催
PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催
PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催Preferred Networks
 
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...PyData
 
analysis on concealing information within non secret data
analysis on concealing information within non secret dataanalysis on concealing information within non secret data
analysis on concealing information within non secret dataVema Reddy
 
Compressed sensing techniques for sensor data using unsupervised learning
Compressed sensing techniques for sensor data using unsupervised learningCompressed sensing techniques for sensor data using unsupervised learning
Compressed sensing techniques for sensor data using unsupervised learningSong Cui, Ph.D
 
Approximate bounded-knowledge-extractionusing-type-i-fuzzy-logic
Approximate bounded-knowledge-extractionusing-type-i-fuzzy-logicApproximate bounded-knowledge-extractionusing-type-i-fuzzy-logic
Approximate bounded-knowledge-extractionusing-type-i-fuzzy-logicCemal Ardil
 
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Daniel Lewis
 
Accelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile SystemsAccelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile SystemsDarian Frajberg
 
A Novel GA-SVM Model For Vehicles And Pedestrial Classification In Videos
A Novel GA-SVM Model For Vehicles And Pedestrial Classification In VideosA Novel GA-SVM Model For Vehicles And Pedestrial Classification In Videos
A Novel GA-SVM Model For Vehicles And Pedestrial Classification In Videosijtsrd
 
Data Steganography for Optical Color Image Cryptosystems
Data Steganography for Optical Color Image CryptosystemsData Steganography for Optical Color Image Cryptosystems
Data Steganography for Optical Color Image CryptosystemsCSCJournals
 
Semi-supervised learning approach using modified self-training algorithm to c...
Semi-supervised learning approach using modified self-training algorithm to c...Semi-supervised learning approach using modified self-training algorithm to c...
Semi-supervised learning approach using modified self-training algorithm to c...IJECEIAES
 
Framework for Contextual Outlier Identification using Multivariate Analysis a...
Framework for Contextual Outlier Identification using Multivariate Analysis a...Framework for Contextual Outlier Identification using Multivariate Analysis a...
Framework for Contextual Outlier Identification using Multivariate Analysis a...IJECEIAES
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakPyData
 
A R T I F I C I A L N E U R A L N E T W O R K S J N T U M O D E L P A P ...
A R T I F I C I A L  N E U R A L  N E T W O R K S  J N T U  M O D E L  P A P ...A R T I F I C I A L  N E U R A L  N E T W O R K S  J N T U  M O D E L  P A P ...
A R T I F I C I A L N E U R A L N E T W O R K S J N T U M O D E L P A P ...guest3f9c6b
 

What's hot (19)

Developing Document Image Retrieval System
Developing Document Image Retrieval SystemDeveloping Document Image Retrieval System
Developing Document Image Retrieval System
 
Unsupervised Feature Learning
Unsupervised Feature LearningUnsupervised Feature Learning
Unsupervised Feature Learning
 
Dynamic Two-Stage Image Retrieval from Large Multimodal Databases
Dynamic Two-Stage Image Retrieval from Large Multimodal DatabasesDynamic Two-Stage Image Retrieval from Large Multimodal Databases
Dynamic Two-Stage Image Retrieval from Large Multimodal Databases
 
PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催
PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催
PFP:材料探索のための汎用Neural Network Potential - 2021/10/4 QCMSR + DLAP共催
 
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
 
Automatic Image Annotation
Automatic Image AnnotationAutomatic Image Annotation
Automatic Image Annotation
 
analysis on concealing information within non secret data
analysis on concealing information within non secret dataanalysis on concealing information within non secret data
analysis on concealing information within non secret data
 
Compressed sensing techniques for sensor data using unsupervised learning
Compressed sensing techniques for sensor data using unsupervised learningCompressed sensing techniques for sensor data using unsupervised learning
Compressed sensing techniques for sensor data using unsupervised learning
 
Approximate bounded-knowledge-extractionusing-type-i-fuzzy-logic
Approximate bounded-knowledge-extractionusing-type-i-fuzzy-logicApproximate bounded-knowledge-extractionusing-type-i-fuzzy-logic
Approximate bounded-knowledge-extractionusing-type-i-fuzzy-logic
 
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
 
Accelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile SystemsAccelerating Deep Learning Inference 
on Mobile Systems
Accelerating Deep Learning Inference 
on Mobile Systems
 
A Novel GA-SVM Model For Vehicles And Pedestrial Classification In Videos
A Novel GA-SVM Model For Vehicles And Pedestrial Classification In VideosA Novel GA-SVM Model For Vehicles And Pedestrial Classification In Videos
A Novel GA-SVM Model For Vehicles And Pedestrial Classification In Videos
 
Data Steganography for Optical Color Image Cryptosystems
Data Steganography for Optical Color Image CryptosystemsData Steganography for Optical Color Image Cryptosystems
Data Steganography for Optical Color Image Cryptosystems
 
J04401066071
J04401066071J04401066071
J04401066071
 
Making Robots Learn
Making Robots LearnMaking Robots Learn
Making Robots Learn
 
Semi-supervised learning approach using modified self-training algorithm to c...
Semi-supervised learning approach using modified self-training algorithm to c...Semi-supervised learning approach using modified self-training algorithm to c...
Semi-supervised learning approach using modified self-training algorithm to c...
 
Framework for Contextual Outlier Identification using Multivariate Analysis a...
Framework for Contextual Outlier Identification using Multivariate Analysis a...Framework for Contextual Outlier Identification using Multivariate Analysis a...
Framework for Contextual Outlier Identification using Multivariate Analysis a...
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
A R T I F I C I A L N E U R A L N E T W O R K S J N T U M O D E L P A P ...
A R T I F I C I A L  N E U R A L  N E T W O R K S  J N T U  M O D E L  P A P ...A R T I F I C I A L  N E U R A L  N E T W O R K S  J N T U  M O D E L  P A P ...
A R T I F I C I A L N E U R A L N E T W O R K S J N T U M O D E L P A P ...
 

Viewers also liked

android os by yogesh jadhav
android os by yogesh jadhavandroid os by yogesh jadhav
android os by yogesh jadhavStudent
 
Secure Multiparty Computation - a technology with promises for privacy
Secure Multiparty Computation - a technology with promises for privacySecure Multiparty Computation - a technology with promises for privacy
Secure Multiparty Computation - a technology with promises for privacyJakob Illeborg Pagter
 
Secure Multiparty Computation or: How I learned to stop worrying and love the...
Secure Multiparty Computation or: How I learned to stop worrying and love the...Secure Multiparty Computation or: How I learned to stop worrying and love the...
Secure Multiparty Computation or: How I learned to stop worrying and love the...Jakob Illeborg Pagter
 
Secure e voting system
Secure e voting systemSecure e voting system
Secure e voting systemMonira Monir
 
Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...
Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...
Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...Ferhat Ozgur Catak
 
Network ve Sistem 101 etkinliği
Network ve Sistem 101 etkinliği Network ve Sistem 101 etkinliği
Network ve Sistem 101 etkinliği Ahmet Han
 
Embracing Distributed Version Control
Embracing Distributed Version ControlEmbracing Distributed Version Control
Embracing Distributed Version ControlNowell Strite
 
IP Security
IP SecurityIP Security
IP SecurityS H
 
Network101 murat arslan
Network101 murat arslanNetwork101 murat arslan
Network101 murat arslanMURAT ARSLAN
 
The Agile Process - Taming Your Process To Work For You
The Agile Process - Taming Your Process To Work For YouThe Agile Process - Taming Your Process To Work For You
The Agile Process - Taming Your Process To Work For YouNowell Strite
 
BSides Philly Finding a Company's BreakPoint
BSides Philly Finding a Company's BreakPointBSides Philly Finding a Company's BreakPoint
BSides Philly Finding a Company's BreakPointAndrew McNicol
 
Verilerimi düzenliyorum
Verilerimi düzenliyorumVerilerimi düzenliyorum
Verilerimi düzenliyorumİsmail Keskin
 
PROJE SÜREÇ YÖNETİMİ
PROJE SÜREÇ YÖNETİMİPROJE SÜREÇ YÖNETİMİ
PROJE SÜREÇ YÖNETİMİturkates
 

Viewers also liked (20)

android os by yogesh jadhav
android os by yogesh jadhavandroid os by yogesh jadhav
android os by yogesh jadhav
 
Secure Multiparty Computation - a technology with promises for privacy
Secure Multiparty Computation - a technology with promises for privacySecure Multiparty Computation - a technology with promises for privacy
Secure Multiparty Computation - a technology with promises for privacy
 
Secure Multiparty Computation or: How I learned to stop worrying and love the...
Secure Multiparty Computation or: How I learned to stop worrying and love the...Secure Multiparty Computation or: How I learned to stop worrying and love the...
Secure Multiparty Computation or: How I learned to stop worrying and love the...
 
Secure e voting system
Secure e voting systemSecure e voting system
Secure e voting system
 
Tablo oluşturma
Tablo oluşturmaTablo oluşturma
Tablo oluşturma
 
Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...
Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...
Dağıtık Sistemler İçin Mahremiyet Korumalı Uç Öğrenme Makinesi Sınıflandırma ...
 
Hesaplamalarım
HesaplamalarımHesaplamalarım
Hesaplamalarım
 
Network ve Sistem 101 etkinliği
Network ve Sistem 101 etkinliği Network ve Sistem 101 etkinliği
Network ve Sistem 101 etkinliği
 
Embracing Distributed Version Control
Embracing Distributed Version ControlEmbracing Distributed Version Control
Embracing Distributed Version Control
 
IP Security
IP SecurityIP Security
IP Security
 
Network101 murat arslan
Network101 murat arslanNetwork101 murat arslan
Network101 murat arslan
 
Visual cryptography1
Visual cryptography1Visual cryptography1
Visual cryptography1
 
The Agile Process - Taming Your Process To Work For You
The Agile Process - Taming Your Process To Work For YouThe Agile Process - Taming Your Process To Work For You
The Agile Process - Taming Your Process To Work For You
 
BSides Philly Finding a Company's BreakPoint
BSides Philly Finding a Company's BreakPointBSides Philly Finding a Company's BreakPoint
BSides Philly Finding a Company's BreakPoint
 
Bilgelik hikayeleri
Bilgelik hikayeleriBilgelik hikayeleri
Bilgelik hikayeleri
 
Phương pháp học đại học
Phương pháp học đại họcPhương pháp học đại học
Phương pháp học đại học
 
Dili kullanmak
Dili kullanmakDili kullanmak
Dili kullanmak
 
Verilerimi düzenliyorum
Verilerimi düzenliyorumVerilerimi düzenliyorum
Verilerimi düzenliyorum
 
Why learn python in 2017?
Why learn python in 2017?Why learn python in 2017?
Why learn python in 2017?
 
PROJE SÜREÇ YÖNETİMİ
PROJE SÜREÇ YÖNETİMİPROJE SÜREÇ YÖNETİMİ
PROJE SÜREÇ YÖNETİMİ
 

Similar to Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data

Cloud computing term paper
Cloud computing term paperCloud computing term paper
Cloud computing term paperHemanth
 
Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...
Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...
Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...IOSR Journals
 
Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...
Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...
Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...IOSR Journals
 
Optimization of latency of temporal key Integrity protocol (tkip) using graph...
Optimization of latency of temporal key Integrity protocol (tkip) using graph...Optimization of latency of temporal key Integrity protocol (tkip) using graph...
Optimization of latency of temporal key Integrity protocol (tkip) using graph...ijcseit
 
Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...
Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...
Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...ijcseit
 
Pretext Knowledge Grids on Unstructured Data for Facilitating Online Education
Pretext Knowledge Grids on Unstructured Data for Facilitating  Online EducationPretext Knowledge Grids on Unstructured Data for Facilitating  Online Education
Pretext Knowledge Grids on Unstructured Data for Facilitating Online EducationIOSR Journals
 
Convolutional neural network based key generation for security of data throug...
Convolutional neural network based key generation for security of data throug...Convolutional neural network based key generation for security of data throug...
Convolutional neural network based key generation for security of data throug...IJECEIAES
 
[Kcc poster] 정준영
[Kcc poster] 정준영[Kcc poster] 정준영
[Kcc poster] 정준영Junyoung Jung
 
Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...
Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...
Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...Bharath Sudharsan
 
Google Deep Learning Innovation Insights from Patents
Google Deep Learning Innovation Insights from PatentsGoogle Deep Learning Innovation Insights from Patents
Google Deep Learning Innovation Insights from PatentsAlex G. Lee, Ph.D. Esq. CLP
 
Distributed firewalls and ids interoperability checking based on a formal app...
Distributed firewalls and ids interoperability checking based on a formal app...Distributed firewalls and ids interoperability checking based on a formal app...
Distributed firewalls and ids interoperability checking based on a formal app...IJCNCJournal
 
PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...
PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...
PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...Thushara Maruthiyat
 
Securing Image Transmission Using in- Compression Encryption Technique
Securing Image Transmission Using in- Compression Encryption TechniqueSecuring Image Transmission Using in- Compression Encryption Technique
Securing Image Transmission Using in- Compression Encryption TechniqueCSCJournals
 
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...Cemal Ardil
 
IRJET-2 Proxy-Oriented Data Uploading in Multi Cloud Storage
IRJET-2 	  Proxy-Oriented Data Uploading in Multi Cloud StorageIRJET-2 	  Proxy-Oriented Data Uploading in Multi Cloud Storage
IRJET-2 Proxy-Oriented Data Uploading in Multi Cloud StorageIRJET Journal
 
Classification of secure encrypted relationaldata in cloud computing
Classification of secure encrypted relationaldata in cloud computingClassification of secure encrypted relationaldata in cloud computing
Classification of secure encrypted relationaldata in cloud computingeSAT Journals
 
Access Control & Encryption In Cloud Environments
Access Control & Encryption In Cloud EnvironmentsAccess Control & Encryption In Cloud Environments
Access Control & Encryption In Cloud EnvironmentsJames Wernicke
 

Similar to Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data (20)

Cloud computing term paper
Cloud computing term paperCloud computing term paper
Cloud computing term paper
 
Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...
Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...
Back-Propagation Neural Network Learning with Preserved Privacy using Cloud C...
 
L017217579
L017217579L017217579
L017217579
 
NETWORJS3.pdf
NETWORJS3.pdfNETWORJS3.pdf
NETWORJS3.pdf
 
Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...
Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...
Double Key Encryption Method (DKEM) Algorithms Using ANN for Data Storing and...
 
Optimization of latency of temporal key Integrity protocol (tkip) using graph...
Optimization of latency of temporal key Integrity protocol (tkip) using graph...Optimization of latency of temporal key Integrity protocol (tkip) using graph...
Optimization of latency of temporal key Integrity protocol (tkip) using graph...
 
Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...
Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...
Optimization of Latency of Temporal Key Integrity Protocol (TKIP) Using Graph...
 
Pretext Knowledge Grids on Unstructured Data for Facilitating Online Education
Pretext Knowledge Grids on Unstructured Data for Facilitating  Online EducationPretext Knowledge Grids on Unstructured Data for Facilitating  Online Education
Pretext Knowledge Grids on Unstructured Data for Facilitating Online Education
 
Convolutional neural network based key generation for security of data throug...
Convolutional neural network based key generation for security of data throug...Convolutional neural network based key generation for security of data throug...
Convolutional neural network based key generation for security of data throug...
 
[Kcc poster] 정준영
[Kcc poster] 정준영[Kcc poster] 정준영
[Kcc poster] 정준영
 
Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...
Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...
Ensemble Methods for Collective Intelligence: Combining Ubiquitous ML Models ...
 
Google Deep Learning Innovation Insights from Patents
Google Deep Learning Innovation Insights from PatentsGoogle Deep Learning Innovation Insights from Patents
Google Deep Learning Innovation Insights from Patents
 
Distributed firewalls and ids interoperability checking based on a formal app...
Distributed firewalls and ids interoperability checking based on a formal app...Distributed firewalls and ids interoperability checking based on a formal app...
Distributed firewalls and ids interoperability checking based on a formal app...
 
PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...
PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...
PRIVACY PRESERVING BACK-PROPOGATION NEURAL NETWORK LEARNING MADE PRACTICAL WI...
 
Securing Image Transmission Using in- Compression Encryption Technique
Securing Image Transmission Using in- Compression Encryption TechniqueSecuring Image Transmission Using in- Compression Encryption Technique
Securing Image Transmission Using in- Compression Encryption Technique
 
PACE-IT, Security+1.4: Common Network Protocols (part 3)
PACE-IT, Security+1.4: Common Network Protocols (part 3)PACE-IT, Security+1.4: Common Network Protocols (part 3)
PACE-IT, Security+1.4: Common Network Protocols (part 3)
 
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
Levenberg marquardt-algorithm-for-karachi-stock-exchange-share-rates-forecast...
 
IRJET-2 Proxy-Oriented Data Uploading in Multi Cloud Storage
IRJET-2 	  Proxy-Oriented Data Uploading in Multi Cloud StorageIRJET-2 	  Proxy-Oriented Data Uploading in Multi Cloud Storage
IRJET-2 Proxy-Oriented Data Uploading in Multi Cloud Storage
 
Classification of secure encrypted relationaldata in cloud computing
Classification of secure encrypted relationaldata in cloud computingClassification of secure encrypted relationaldata in cloud computing
Classification of secure encrypted relationaldata in cloud computing
 
Access Control & Encryption In Cloud Environments
Access Control & Encryption In Cloud EnvironmentsAccess Control & Encryption In Cloud Environments
Access Control & Encryption In Cloud Environments
 

More from Ferhat Ozgur Catak

Dağıtık Servis Dışı Bırakma Saldırıları
Dağıtık Servis Dışı Bırakma SaldırılarıDağıtık Servis Dışı Bırakma Saldırıları
Dağıtık Servis Dışı Bırakma SaldırılarıFerhat Ozgur Catak
 
Veritabanı Sızma Testleri - Hafta 3
Veritabanı Sızma Testleri - Hafta 3Veritabanı Sızma Testleri - Hafta 3
Veritabanı Sızma Testleri - Hafta 3Ferhat Ozgur Catak
 
Veritabanı Sızma Testleri - 2
Veritabanı Sızma Testleri - 2Veritabanı Sızma Testleri - 2
Veritabanı Sızma Testleri - 2Ferhat Ozgur Catak
 
Veritabanı Sızma Testleri - Keşif
Veritabanı Sızma Testleri - KeşifVeritabanı Sızma Testleri - Keşif
Veritabanı Sızma Testleri - KeşifFerhat Ozgur Catak
 
Sızma Testi ve Güvenlik Denetlemeleri - Temel Linux Bilgisi
Sızma Testi ve Güvenlik Denetlemeleri - Temel Linux BilgisiSızma Testi ve Güvenlik Denetlemeleri - Temel Linux Bilgisi
Sızma Testi ve Güvenlik Denetlemeleri - Temel Linux BilgisiFerhat Ozgur Catak
 
Sızma Testi ve Güvenlik Denetlemeleri - Giriş
Sızma Testi ve Güvenlik Denetlemeleri - GirişSızma Testi ve Güvenlik Denetlemeleri - Giriş
Sızma Testi ve Güvenlik Denetlemeleri - GirişFerhat Ozgur Catak
 
Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...
Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...
Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...Ferhat Ozgur Catak
 
Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...
Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...
Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...Ferhat Ozgur Catak
 
Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...
Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...
Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...Ferhat Ozgur Catak
 
Korelasyon tabanlı nitelik seçimi
Korelasyon tabanlı nitelik seçimiKorelasyon tabanlı nitelik seçimi
Korelasyon tabanlı nitelik seçimiFerhat Ozgur Catak
 

More from Ferhat Ozgur Catak (19)

Siber Güvenlik ve Yapay Zeka
Siber Güvenlik ve Yapay ZekaSiber Güvenlik ve Yapay Zeka
Siber Güvenlik ve Yapay Zeka
 
Siber Güvenlik ve Yapay Zeka
Siber Güvenlik ve Yapay ZekaSiber Güvenlik ve Yapay Zeka
Siber Güvenlik ve Yapay Zeka
 
Windows Hacking 2
Windows Hacking 2Windows Hacking 2
Windows Hacking 2
 
Windows hacking 1
Windows hacking 1Windows hacking 1
Windows hacking 1
 
Pivoting ve Tunneling
Pivoting ve TunnelingPivoting ve Tunneling
Pivoting ve Tunneling
 
Ddos Sızma Testleri - 2
Ddos Sızma Testleri - 2Ddos Sızma Testleri - 2
Ddos Sızma Testleri - 2
 
Dağıtık Servis Dışı Bırakma Saldırıları
Dağıtık Servis Dışı Bırakma SaldırılarıDağıtık Servis Dışı Bırakma Saldırıları
Dağıtık Servis Dışı Bırakma Saldırıları
 
Sosyal muhendislik 1
Sosyal muhendislik 1Sosyal muhendislik 1
Sosyal muhendislik 1
 
Veritabanı Sızma Testleri - Hafta 3
Veritabanı Sızma Testleri - Hafta 3Veritabanı Sızma Testleri - Hafta 3
Veritabanı Sızma Testleri - Hafta 3
 
Veritabanı Sızma Testleri - 2
Veritabanı Sızma Testleri - 2Veritabanı Sızma Testleri - 2
Veritabanı Sızma Testleri - 2
 
Veritabanı Sızma Testleri - Keşif
Veritabanı Sızma Testleri - KeşifVeritabanı Sızma Testleri - Keşif
Veritabanı Sızma Testleri - Keşif
 
Kesif ve Zafiyet Tarama
Kesif ve Zafiyet TaramaKesif ve Zafiyet Tarama
Kesif ve Zafiyet Tarama
 
Sızma Testi ve Güvenlik Denetlemeleri - Temel Linux Bilgisi
Sızma Testi ve Güvenlik Denetlemeleri - Temel Linux BilgisiSızma Testi ve Güvenlik Denetlemeleri - Temel Linux Bilgisi
Sızma Testi ve Güvenlik Denetlemeleri - Temel Linux Bilgisi
 
Sızma Testi ve Güvenlik Denetlemeleri - Giriş
Sızma Testi ve Güvenlik Denetlemeleri - GirişSızma Testi ve Güvenlik Denetlemeleri - Giriş
Sızma Testi ve Güvenlik Denetlemeleri - Giriş
 
Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...
Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...
Eşle/İndirge Yöntemi Kullanılarak Destek Vektör Makinesi Algoritması ile Yü...
 
Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...
Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...
Rassal Bölümlenmiş Veri Üzerinde Aşırı Öğrenme Makinesi ve Topluluk Algoritma...
 
MapReduce based SVM
MapReduce based SVMMapReduce based SVM
MapReduce based SVM
 
Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...
Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...
Fuzzy Analytic Hierarchy Based DBMS Selection In Turkish National Identity Ca...
 
Korelasyon tabanlı nitelik seçimi
Korelasyon tabanlı nitelik seçimiKorelasyon tabanlı nitelik seçimi
Korelasyon tabanlı nitelik seçimi
 

Recently uploaded

办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一fhwihughh
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.natarajan8993
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...limedy534
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxdolaknnilon
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Colleen Farrelly
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSINGmarianagonzalez07
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 

Recently uploaded (20)

办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
办理学位证纽约大学毕业证(NYU毕业证书)原版一比一
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptx
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
2006_GasProcessing_HB (1).pdf HYDROCARBON PROCESSING
 
Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 

Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data

  • 1. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, Turkey Nov. 10 2015 The 2015 International Data Mining and Cybersecurity Workshop With ICONIP2015 Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 2. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Table of Contents 1 Introduction Secure Multiparty Computation Contributions 2 Preliminaries ELM Secure Multi Party Computation Secure Multi-Party Addition 3 Privacy-preserving ELM over vertically partitioned data Privacy-preserving ELM 4 Experiments Experimental setup Simulation Results 5 Conclusions Conclusions Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 3. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Secure Multiparty Computation Contributions Table of Contents 1 Introduction Secure Multiparty Computation Contributions 2 Preliminaries ELM Secure Multi Party Computation Secure Multi-Party Addition 3 Privacy-preserving ELM over vertically partitioned data Privacy-preserving ELM 4 Experiments Experimental setup Simulation Results 5 Conclusions Conclusions Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 4. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Secure Multiparty Computation Contributions Secure Multiparty Computation (SMC) Definition SMC : The goal of creating methods for parties to jointly compute a function over their inputs while keeping those inputs private. In an MPC, a given number of participants, p1, p2, · · · , pN each has private data, respectively d1, d2, · · · , dN Participants want to compute the value of a public function on that private data: F(d1, d2, ..., dN ) while keeping their own inputs secret. Challenges : To protect each participant’s private data, and intermediate results The computation/communication cost introduced to each participant shall be affordable Training data is arbitrarily partitioned Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 5. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Secure Multiparty Computation Contributions Contributions Main contributions of the work Privacy-preserving Extreme Learning Machine (ELM) training model Global ELM classification model from the distributed data sets in multiple parties Training data set is vertically partitioned among the parties The final distributed model is constructed at an independent party Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 6. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Table of Contents 1 Introduction Secure Multiparty Computation Contributions 2 Preliminaries ELM Secure Multi Party Computation Secure Multi-Party Addition 3 Privacy-preserving ELM over vertically partitioned data Privacy-preserving ELM 4 Experiments Experimental setup Simulation Results 5 Conclusions Conclusions Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 7. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Extreme Learning Machine (ELM) Learning Without Iterative Tuning All hidden node parameters can be randomly generated without the knowledge of the training data. That is, for any continuous target function f and any randomly generated sequence limL→∞ ||f (x) − fL(x)|| = limL→∞ ||f (x) − L i=1 βi G(ai , bi , x)|| = 0 holds with probability one if βi is chosen to minimize ||f (x) − fL(x)||, ∀i G.-B. Huang, et al., ”Universal approximation using incremental constructive feedforward networks with random hidden nodes,” IEEE Transactions on Neural Networks, vol. 17, no. 4, pp. 879-892, 2006. G.-B. Huang, et al., ”Convex incremental extreme learning machine,” Neurocomputing, vol. 70, pp. 3056-3062, 2007. G.-B. Huang, et al., ”Enhanced random search based incremental extreme learning machine,” Neurocomputing, vol. 71, pp. 3460-3468, 2008. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 8. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Extreme Learning Machine (ELM) Figure: Generalized SLFN Mathematical Model For N arbitrary distinct samples (xi , ti ) ∈ Rn × Rm, SLFNs with L hidden nodes each with output function, G(ai , bi , x) are mathematically modeled as L i=1 βi G(ai , bi , xj ) = tj , j = 1, ..., N (1) (ai , bi ): hidden node parameters. βi : the weight vector connecting the ith hidden node and the output node. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 9. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Extreme Learning Machine (ELM) Mathematical Model L i=1 βi G(ai , bi , xj ) = tj , j = 1, ..., N is equivalent to Hβ = T where,    h(x1) ... h(xN)    =    G(a1, b1, x1) · · · G(aL, bL, x1) ... ... ... G(a1, b1, xN) · · · G(aL, bL, xN)    N×L (2) β =    βT 1 ... βT L    L×m ve T =    tT 1 ... tT N    N×m (3) H, is called the hidden layer output matrix of the neural network, the ith column of H is the output of the ith hidden node with respect to inputs , x1, ..., xn Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 10. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Extreme Learning Machine (ELM) Three-Step Learning Model Given a training set D = {(xi , ti )|xi ∈ Rn , ti ∈ Rm , i = 1, · · · , N}, hidden node output function G(a, b, x), and the number of hidden nodes L, 1 Assign randomly hidden node parameters (ai , bi ), i = 1, · · · , L. 2 Calculate the hidden layer output matrix H. 3 Calculate the output weight β = Ht T. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 11. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Secure Multi Party Computation Secure Multi-Party Computation The problem of n players to compute an agreed function f of their inputs In vertically partitioned data, each party holds different attributes of same data set. The partition strategy is shown in Figure 2. x1,1 · · · x1,t−1 · · · x1,t · · · x1,k x2,1 · · · x2,t−1 · · · x2,t · · · x2,k ... ... ... ... ... ... ... xm,1 · · · xm,t−1 · · · xm,t · · · xm,k               P1 · · · Pk D = Figure: Vertically partitioned data set D. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 12. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Secure Multi-Party Addition I Secure Multi-Party Addition Assume k ≥ 3 parties, P0, · · · , Pk−1, with party Pi holding value vi Aim is to compute v = k−1 i=0 vi Sum of vi lies in F P0 randomly chooses a number R ∈ F P0 adds R to its local value v0, Sends v0 = R + v0mod|F| to P1 The remaining parties Pi , i = 1, · · · , k − 1 Pi receives V = R + i−1 j=0 vj mod|F| Pi sends R + j=1 ivj mod|F| = (vi + V )mod|F| Finally, P0, subtracts R from the final message to compute actual results. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 13. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Secure Multi-Party Addition II Party0 x0 , R ∈ F Party1 x1 Party2 x2 Partyk xk V = R + x0mod|F| V = R + i−1 j=0 xjmod|F| (xi + V )mod|F| Figure: Secure Multi-Party Addition. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 14. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions ELM Secure Multi Party Computation Secure Multi-Party Addition Secure Multi-Party Addition III Algorithm 1: Secure multi-party addition 1: procedure SMA(P) 2: P0 : R ← rand(F) P0 randomly chooses a number R 3: V ← R + x0 mod F 4: P0 sends V to node P1 5: for i = 1, · · · , k − 1 do 6: Pi receives V = R + i−1 j=0 xj mod F 7: Pi computes V = R + i j=1 xj mod F = ((xi + V ) mod F) 8: Pi sends V to node Pi+1 9: P0 : V ← (V − R) = (V − R mod F) Actual addition result 10: end procedure Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 15. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Privacy-preserving ELM Table of Contents 1 Introduction Secure Multiparty Computation Contributions 2 Preliminaries ELM Secure Multi Party Computation Secure Multi-Party Addition 3 Privacy-preserving ELM over vertically partitioned data Privacy-preserving ELM 4 Experiments Experimental setup Simulation Results 5 Conclusions Conclusions Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 16. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Privacy-preserving ELM Privacy-preserving ELM I 1 Master party creates weight matrix, W ∈ RL×N 2 Master party distributes partition W with same feature size for each parties. 3 Party P0 creates a random matrix, R =    rand1,1(F) · · · rand1,L(F) ... ... ... randN,1(F) · · · randN,L(F)    N×L 4 Party P0 creates perturbated output, V = R +    x0 1 · w0 1 + b0 1 · · · x0 1 · w0 L + b0 L ... ... ... x0 N · w0 1 + b0 1 · · · x0 N · w0 L + b0 L    5 for i = 1, · · · , k − 1 Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 17. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Privacy-preserving ELM Privacy-preserving ELM II Pi computes V = V +    xi 1 · wi 1 + bi 1 · · · xi 1 · wi L + bi L ... ... ... xi N · wi 1 + bi 1 · · · xi L · wi N + bi N    Pi sends V to Pi+1 6 P0 subtracts random matrix, R, from the received matrix V. H = (V − R) mod F 7 Hidden layer node weight vector, β, is calculated. β = H† · T Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 18. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Privacy-preserving ELM Privacy-preserving ELM III P arty0 x0 , w, H0 ,R ∈ F, Party1 x1 , H1 , w Party2 x2 , H2 , w Partyk xk−1 , Hk−1 , w V0 = R + H0 mod|F| V1 = V0+H1 mod|F| V2 = V1 + H2 mod|F| Vk = Vk−1 + Hk mod|F| Hi =     G(w1, b1, xi 1) · · · G(wL, bL, xi 1) . . . ... . . . G(w1, b1, xi N ) · · · G(wL, bL, xi N )     N×L R =     rand1,1(F) · · · rand1,L(F) . . . ... . . . randN,1(F) · · · randN,L(F)     N×L H = (V − R) mod F Figure: Overview of privacy-preserving ELM learning. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 19. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Experimental setup Simulation Results Table of Contents 1 Introduction Secure Multiparty Computation Contributions 2 Preliminaries ELM Secure Multi Party Computation Secure Multi-Party Addition 3 Privacy-preserving ELM over vertically partitioned data Privacy-preserving ELM 4 Experiments Experimental setup Simulation Results 5 Conclusions Conclusions Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 20. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Experimental setup Simulation Results Experimental setup I Our approach is applied to six different data sets to verify its model effectivity and efficiency. Table: Description of the testing data sets used in the experiments. Data set #Train #Classes #Attributes australian 690 2 14 colon-cancer 62 2 2,000 diabetes 768 2 8 duke breast cancer 44 2 7,129 heart 270 2 13 ionosphere 351 2 34 Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 21. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Experimental setup Simulation Results Simulation Results I The number of party size, k: from 3 to number of feature n, of the data set For instance, k = 3, and n = 14, then the first two party have 5 attributes, and last party has 4 attributes. The accuracy of secure multi-party computation based ELM is exactly same for the traditional ELM training algorithm. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 22. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Experimental setup Simulation Results Simulation Results II Figure shows results of our simulations. Time scale becomes its steady state position when number of parties k, moves closer to number of attributes, n. 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 10 −1 10 0 10 1 10 2 10 3 AttributeS ize(n) P artyS ize(k) Timescale australian colon−cancer diabetes duke heart ionosphere Figure: Vertically partitioned data set D. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 23. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Conclusions Table of Contents 1 Introduction Secure Multiparty Computation Contributions 2 Preliminaries ELM Secure Multi Party Computation Secure Multi-Party Addition 3 Privacy-preserving ELM over vertically partitioned data Privacy-preserving ELM 4 Experiments Experimental setup Simulation Results 5 Conclusions Conclusions Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 24. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Conclusions Conclusions Summary ELM learning algorithm, a new method. ELM outperforms traditional Single Layer Feed-forward Neural-networks and Support Vector Machines for Big Data 1 In all fields that ELM is applied (i.e. medical records, business, government), privacy is a major concern. Conclusions Privacy-preserving learning model is proposed in vertically partitioned data In multi-party partitioning without sharing the data of each site to the others. Master party divides weight vector, and each party calculates the activation function result with its data and weight vector. 1Cambria, Erik, et al. ”Extreme learning machines [trends & controversies].” Intelligent Systems, IEEE 28.6 (2013): 30-59. Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin
  • 25. Introduction Preliminaries Privacy-preserving ELM over vertically partitioned data Experiments Conclusions Conclusions Thank You Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr Ferhat ¨Ozg¨ur C¸atak ozgur.catak@tubitak.gov.tr T¨UB˙ITAK - B˙ILGEM - Cyber Security Institute Kocaeli, TurkeySecure Multi-Party Computation Based Privacy Preserving Extreme Learnin