Name: Dijana PETROVSKA-DELACRETAZ

Institution : INSTITUT TELECOM, T&M SudParis

She obtained her M.S. degree in Physics in 1981 from the Swiss Federal Institute of Technology (EPFL). From 1982 to 1986, she worked as a research assistant in the Polymer Laboratory, EPFL. In 1995, she received a grant for women re-insertion of the Swiss NSF, starting a new research activity in speech processing at the EPFL-LANOS laboratory. From 2000, after one year spent as a consultant at AT&T Speech Research Laboratories, and another year in ENST-Paris, she was working as a senior scientist in the Informatics Department of the Fribourg University (DIUF), in Switzerland. Since 2004 she holds an Assistant Professor position in Institut Télécom T&M SudParis (ex GET-INT).

Her research activities are mainly oriented towards signal processing, pattern recognition and data-driven machine learning methods, exploited for different applications such as speech, speaker and language recognition, very low-bit speech compression, biometrics (2D and 3D face and voice), crypto-biometrics, and privacy preserving and cancelable biometrics. The results are evaluated using a performance evaluation framework designed to provide comparable and reproducible results. She is a co-inventor of 2 international patents, and since 2004, she is an author/coauthor of 1 book, 4 journals/book chapters and 17 conference proceedings.

Publications :

S. Kanade, D. Camara, E. Krichen, D. Petrovska-Delacrétaz, and B. Dorizzi, "Three factor scheme for biometric-based cryptographic key regeneration using iris", In The 6th Biometrics Symposium 2008 (BSYM2008), September 2008.

D. Petrovska-Delacrétaz, G. Chollet and B.Dorizzi (eds.)
”Guide to Biometric Reference Systems and Performance Evaluation”, DOI 10.1007/978-1-84800-292-0 7, Springer Science+Business Media LLC 2009

Combining biometrics and cryptography for privacy protecting biometric applications and cryptographic key regeneration

Biometrics needs template protection, revocability and template diversity

With the widespread use of biometrics, more and more concerns are being raised about the privacy of the personal biometric data. Conventional biometric systems store biometric templates in a database. This may lead to the possibility of tracking personal information stored in one database by getting access to another database through cross-database matching. Moreover, biometrics data are permanently associated with the user. Hence if they are stolen, they are lost permanently and become unusable in that system and possibly in all other systems based on that biometrics.

In order to overcome these shortcomings, we propose a two factor scheme (biometrics and password) to generate revocable, cancelable, and privacy preserving iris templates.

Cryptography has not a strong link between authenticator and user identity, and repudiation is possible

Combining biometrics and cryptography could lead to generate cryptographic keys using biometric data. We propose a three factor scheme (smart card, iris biometric data and password) for biometric-based cryptographic key regeneration.

The validity of the proposed schemes are tested on different publicly available iris databases, including the NIST-ICE database.