Professional Documents
Culture Documents
CHAPTER I & II
Presentation by Tamer Uz
Chapter I
Introduction
Outline
Descriptions
Authentication
Overview of Biometric Systems
Biometric Identification
Biometric Verification
Biometric Enrollment
Biometric System Security
Descriptions
Biometrics: Science of identifying, or verifying the
identity of, a person based on physiological or
behavioral characteristics.
Descriptions
Authorization: Authentication:
Permission or Validating or figuring
approval. out the identity of a
person.
Authentication
There are 3 traditional way of verifying the
identity of a person:
Possessions (keys, passports, smartcards , …)
Knowledge
Secret (passwords, pass phrases, …)
Non-secret (user Id, mothers maiden name, favorite
color)
Biometrics
Physiological (fingerprints, face, iris, …)
Behavioral (walking, keystroke pattern, talking, …)
Authentication
The 3 modes of authentication are sometimes
combined
User id + password
ATM card + password
Passport + face picture and signiture
Authentication
There are two different authentication methods in
biometrics
1. Universality
2. Uniqueness
3. Permanence
4. Collectability
5. Acceptability
Overview of Biometric Systems
Biometric Identifiers
Overview of Biometric Systems
Biometric Subsystems
Biometric readers (sensors)
Feature extractors
Feature Matchers
Overview of Biometric Systems
A generalized diagram of a biometric system is as
follows:
Overview of Biometric Systems
Design Issues:
4 basic design specifications of biometric systems are
System accuracy
How often the system accepts an imposter (FAR)
How often the system rejects a genuine user (FRR)
Computational Speed
Exception Handling
Failure to use (FTU)
Failure to enroll (FTE)
Failure to acquire (FTA)
System Cost
Overview of Biometric Systems
Engineering Questions - What feature set is amenable for automatic
matching?
- Trusting people/biometrics?
- Given the input data how to extract the features
- Which biometrics is best for a given from it?
application?
- How to define a matching metric that translates the
- How are the error numbers that are intuition of “similarity” among the patterns?
reported for different biometrics to be
interpreted? - How to implement the matching metric?
- Are new security holes created because of - Organization of the database?
the use of the biometrics?
- Methods for searching the database?
- How to achieve a low exception rate?
- Security?
- How to acquire the biometrics and how to
do it in a convenient way? - Privacy?
Biometric Identification
Biometric identification is based only on biometric
credentials.
Biometric Identification
Biometric identification system can be used in
two different modes
• Positive identification
• Authorization of a group without id
• Negative identification
• Most Wanted List
Biometric Verification
Biometric verification differs from biometric
identification in that the presented biometric is only
compared with a single enrolled biometric entity
which matches the input id
Biometric Verification
There are two possible database configurations for the
verification systems
Authentication
and
Biometrics
Outline
Descriptions
Secure Authentication Protocols
Access Control Security Services
Authentication Methods
Authentication Protocols
Matching Biometric Samples
Verification by Humans
Passwords vs. Biometrics
Hybrid Methods
Descriptions
Authorization: Permission to access a resource
Mutually agreed
Unambiguous
Non-repudiation
Confidentiality
Authentication Methods
Possession (P)
Knowledge (K)
Biometrics (B)
Authentication Protocols
Authentication protocol is the tasks the user and the
access point has to perform to be able to determine
whether the user has enough credentials or not.
• Negative identification.
• Therefore several tokens P1, B1, K1, P2, K2, B2 etc. should
be matched with the ones in the file.
Matching Biometric Samples
Verification
• Id + B is provided. (Sometimes K too)
• The template corresponding the Id is retrieved from
the database
• If s(B,Bi)>T pass, else fail.
Matching Biometric Samples
Continuity of Identity
• Surveillance cameras
Verification by Humans
By looking at the biometrics (face, signatures…)
Face verification error rate 1:1000
Signature verification is not very secure
Passwords versus Biometrics
Passwords: Exact match
Biometrics: Probabilistic match
FAR, FRR
Hybrid Methods
More than one identifier is used {P, K, B}
Two Remarks
B with {P, K}. Reduces identification to
verification (from 1:many to 1:1)
B1 with B2. Results in better ROCs than using
only B1 or only B2
Combination of matching scores is an
application specific problem
QUESTIONS?