This document provides an overview of biometric authentication, including a brief history, importance, types, methods, risks, and conclusions. It discusses how biometric authentication measures intrinsic characteristics of users to validate their identity. The types include physiological (fingerprints, iris, face) and behavioral (voice, typing patterns). It outlines some common biometric methods, their strengths and weaknesses, and examples of appropriate uses. In conclusion, while not foolproof, biometric authentication offers stronger verification than passwords if a balance between security and privacy is achieved.
4. Introduction
• Word biometric is derived from Greek words
bios mean life and metrics mean measure
• Therefore biometric authentication is defined
measuring of physiological or behavioral
properties related to particular entity to verify
or authenticate the entity.
5. Quick Look at History
• During the construction of great Pyramid Khufu workers
need to be authenticated for allowance
• 14th century in china, they use to save palm and foot
prints on clay blocks
• In 1890 a Persian police man Alphonse Bertillon provided
the basics to recognize the fingerprints
• 1892 Francis developed a classified system for finger
prints
• In 1896 Based on Bertillon study Aziz-ul-Haq developed
first systematic finger prints system for Edward Henry ,a
colonial of British Army in Bengal, India.
6. Quick Look at History
• 1936 Frank Burch gave a concept of using Iris
patterns for the recognition of an individual
• 1960 work on face recognition and voice
recognition
• 1965 automated system for signature
recognition
• Rapid development in biometric authentication
in 70’s
7. Quick Look at History
• 1985 patent for hand identification
• 1995 iris prototype become available as a
commercial product
• 1996 hand geometry used in Olympic games
held in Atlanta.
• First major success.
8. Quick Look at History
• 2000,first face recognition commercial product
• 2000,first research paper on vascular patterns
for recognition
• Modern biometrics based on computing have
developed now.
9. Importance of Biometric
Authentication
• Security is becoming important in business and
every field of life
• Fraud detection
• A person can claim multiple identities to get
more resources
• Biometric properties cannot be stolen unlike
passwords and keys
• After 9/11 rapid development on Biometric
Authentication
10. Types of Biometric Authentication
Biometric applications available today are
categorized into 2 sectors
• Physiological: Iris, Fingerprints, Hand Geometry,
Retinal ,Face recognition etc.
• Behavioral: Voice, Typing pattern etc.
11. Physiological Biometrics
Authentication
• A biometrics which use a physical trait, such
as a fingerprint, iris, hand or face for
recognition. The physical trait is analyzed,
measured and digitally stored.
14. Disadvantages
• Dirt , grime and wounds
• Placement of finger
• Too big a database to process
• Can be spoofed
15. Hand Geometry
• Geometry of users hands
• More reliable than fingerprinting
• Balance in performance and usability
• Very large scanners
16. Retinal Scanning
• Scans retina(the innermost coat of the back
part of the eye) into database
• User looks straight into retinal reader
• It checks the pattern of blood vessels of eye
retina.
• Scan using low intensity light
• Very efficient – cant be spoofed!
• User has to look “directly”
17. Iris Scanning
• Scans unique pattern of iris the colored ring of
muscle
• Iris is colored and visible from far
• No touch required
• The patterns of one person's two eyes are
quite different from each other and even
genetically identical twins have different iris
patterns.
• Contact lenses an issue
18.
19. Face Recognition
• User faces camera
• Neutral expression required
• Appropriate lighting and position
• Algorithms for processing
20.
21. Other Physiological Biometrics
• Palm print
• Hand vein
• DNA
• Thermal imaging
• Ear shape
• Human Odor Recognition
• Fingernail bed
22. Palm Print
• Palm print verification is a slightly different
implementation of the fingerprint technology.
23. Hand Vein
• Hand vein geometry is based on the fact that
the vein pattern is distinctive for various
individuals.
24.
25. DNA
• DNA (Deoxyribose Neucleic Acid)
authentication is very popular at present and
requires a form of tissue, blood or other bodily
sample.
26. Behavioral Biometrics
• Biometrics that is based on a behavioral trait of
an individual.
• Acquired over time by an individual.
• A reflection of an individual’s psychology.
29. How it works
• Speed
• Direction
• Pressure
• Acceleration
• length of the strokes
• Dynamics number of strokes and their duration
30. Advantages
• Unique style of doing Signature.
• One does not know how to write signature
even after looking at it.
31. Disadvantages
• Signature variable with Age, illness, emotions
• Requires high quality hardware
• High FRR as signatures are very dynamic
• Low Accuracy.
32. Voice Recognition
• A Biometric identification by electronically
recording and graphically representing a
person's voice.
33. Voice Recognition
• Voice prints : The unique characteristic of individual.
• User’s voice print is stored in database.
• Enroll by speaking some phrases.
• System Compares the voiceprints.
• Speech input
• Speaking style
• Pitch
• Frequency
• Natural tone
35. Typing Patterns
• A method of verifying the identity of an
individual by their typing rhythm.
• System can verify the user at the log-on stage
or it can Continuously monitor the typist.
36. Typing Patterns
• User typing pattern
• Different characteristics
• Speed ( time durations between the keystrokes )
• Press and Release Rate
• Frequency of errors (use of backspace)
• Use of num pad
• Order in which user presses shift key to get capital letters
• Unique patterns are generated
• Comparisons
• Cheap
• Continuously check the user
37. Disadvantages
• For recognition a large amount of keystroke
data is needed
• Unnecessary comparisons with all existing
users
• Not very scalable
• FRR is high (Speed and Frequency of errors
can vary)
• Can be spoofed – by simple technology
(recorders)
38. Gaits
• Gait is an attractive biometric feature for
human identification at a distance.
• Gait is a particular way or manner
of moving on foot.
• Movements of a person's
various body parts over time
39. Advantages
• Perceivable at a distance
• Non-contact
• Non-invasive ( without interfering human
body)
• Can identify among a group of people
41. General Look on Biometrics
Iris
• Strengths
Very stable over time
Uniqueness
• Weakness
Requires user training
Dependant on a single vendor’s technology
42. General Look on Biometrics
• Iris
• Usability
Information security access control,
especially for Federal Institutions and
government agencies.
43. General Look on Biometrics
Fingerprint
• Strengths
Small template (less than 500 bytes)
Small sensors
• Weakness
Physical contact required
• Usability
Physical access control
Association with criminal justice
44. General Look on Biometrics
Voice
• Strengths
Low training
Microphone can be built into PC or mobile device
• Weaknesses
Changes with time, illness stress or injury
Large template unsuitable for recognition
• Usability
Mobile phones
Telephone banking
45. General Look on Biometrics
Signatures
• Strengths
• High user acceptance
Minimal training
• Weaknesses
Unstable over time
Occasional erratic variability
Enrollment takes times
• Usability
Portable devices with stylus input
46. General Look on Biometrics
Face
• Strengths
Universally present
• Weaknesses
Cannot distinguish identical siblings
Religious or cultural prohibitions
• Usability
Physical access control
47. General Look on Biometrics
Hand
• Strengths
Small template (approximately 10 bytes)
Unaffected by skin condition
• Weaknesses
Physical size of acquisition device
Physical contact required
• Usability
Physical access control
Time and attendance
49. Conclusion
• All authentication methods are prone to errors.
Nevertheless, reliable user authentication must
ensure that an attacker cannot masquerade as a
legitimate user
• Biometrics is uniquely bound to individuals and
may offer organizations a stronger method of
authentication
• Biometric systems are not foolproof; they can be
compromised by:
Submission of another person’s biometric
Submission of enrollee’s biometric with the
user under duress or incapacitated
• A prudent balance between Security and Privacy
needs to be achieved
50. References
• Biometrics History published by NSTC
subcommittee on Biometrics
date:7 August 2006
www.biometrics.gov
• Biometric Authentication
Technology and Evaluation –
Term Project CS574
Spring 2003
San Diego State University
Uwe Bubeck Dina Sanchez
51. References
• Biometrics and Authentication slides of
Shivani Kirubanandan
• Authentication: Overview slides of Paul Bui
• Biometric Authentication Systems
by Zdeneˇk Rˇ íha and Václav Matyáš FIMU
Report Series November 2000