|
Biometrics
Biometrics
is a new field aiming to recognize a person from his/her biological traits
such as fingerprint, iris, retina, face, handshape, signature, keystroke
dynamics,... It is increasingly used in identity verification, while also
drawing concerns about a loss of privacy. We have developed verification
systems for online and offline signatures, and fingerprints.
A newly studied aspect of biometrics is the issue of privacy:
what happens if someone steals your fingerprint? You cannot replace nor
revoke it! We study methods to prevent privacy loss that accompany the
benefits of biometrics (e.g. cancelable biometrics, combined biometrics,
fuzzy vault etc.). Biometric
cryptosystems, systems combining biometrics and cryptography, tries to
achieve cryptographic systems based on biometrics, and also address the
privacy problem as well.
The
online signature verification system we developed has won the first place
at The First
International Signature Verification Competition (SVC 2004) organized in
conjunction with the First International
Conference on Biometric Authentication (ICBA 2004) .
Related papers:
Multi-biometric templates:
“Multimodal Biometric Templates for
Verification Using Fingerprint and Voice”, E. Camlikaya,
A. Kholmatov,
B. Yanikoglu,
SPIE Defense & Security: Biometric Technology For Human Identification
V, 16-20 March 2008, Orlando FL, USA..
In this paper, we combine
the voice and fingerprint of a person to obtain a multi-biometric template
which is both more secure and alleviates privacy concerns.
“Combining
Multiple Biometrics to Protect Privacy”, Berrin Yanikoglu and Alisher
Kholmatov, Proceedings of ICPR-BCTP Workshop, Cambridge, England, Aug 2004. bibtex
A precursor to the above.
Fuzzy Vault:
“Realization of Correlation Attack Against
Fuzzy Vault”, A. Kholmatov and B. Yanikoglu,
Security, Forensics, Steganography, and Watermarking of
Multimedia Contents X, Electronic Imaging, 27-31 Jan. 2008, San Jose CA,
USA.
Shows
the vulnerability of the Fuzzy Vault scheme againsr correlation attacks.
"Secret sharing using biometric
traits", A. Kholmatov, B. A. Yanikoglu, E. Savas, A. Levi,
Biometric Technology For Human Identification III, 18 April 2006, Orlando,
Florida USA, In Proceedings of SPIE Vol. #6202.
In this paper, we implement the Fuzzy Vault
with fingerprints and show how multiple people can share a secret within
this framework. The Fuzzy Vault
implementation does not make any simplifying assumptions.
Online signatures:
“An Individuality Model for Online
Signatures”, A. Kholmatov
and B. Yanikoglu,
SPIE Defense & Security: Biometric Technology For Human Identification
V, 16-20 March 2008, Orlando FL, USA.
Estimates
the guessing entropy of online signatures: how hard is it to guess
someone’s signature? Is it better than a 4-digit ATM pin?...
“SUSIG: An On-line Handwritten
Signature Database, Associated Protocols and Benchmark Results”,
A. Kholmatov
and B. Yanikoglu,
Pattern Analysis and Applications, 2008.
Describes
the protocols and benchmark results for the SUSIG database.
"Identity
authentication using improved online signature verification method",
Alisher Kholmatov and Berrin Yanikoglu Pattern
Recognition Letters, Vol 26(15), pp 2400-2408, Nov. 2005
Thesis supervised:
"Privacy Protecting Biometric
Authentication Systems",
PhD Thesis, Alisher Kholmatov, Sabanci University,
2008.
"Biometric
Identity Verification Using On-Line & Off-Line Signature Verification",
Alisher Kholmatov, Sabanci University, July, 2003: (abstract in English)(abstract
in Turkish)
bibtex
TÜBİTAK
Project (No: 105 E 165 Duration: 6/2006-6/2008): “Privacy Protecting Biometric Authentication
Systems”.
|
