IAPR/IEEE Winter School on Biometrics 2020

Biometric Presentation Attack Detection

Slides (pdf)  Size: 93.8MB

Abstract

In Biometrics, presentation attacks (also coined as spoofing) are now widely accepted to be of two kinds: impersonation, where the attacker attempts to impersonate the victim, and obfuscation, where the goal of the attacker is to avoid being recognised. The vulnerability of state-of-the-art recognition to presentation attacks (PA) have been already demonstrated and presentation attack detection (PAD) is now a growing research topic. In this talk we will review PA techniques published in the literature mostly for face biometrics, vulnerability assessment and introduce several PAD methods.


Biography

Dr Sébastien Marcel ( http://www.idiap.ch/~marcel — IEEE Senior Member ) received the Ph.D. degree in signal processing from Université de Rennes I in France (2000) at CNET, the research center of France Telecom (now Orange Labs). He is currently interested in pattern recognition and machine learning with a focus on biometrics security and privacy.

He is a senior researcher at the Idiap Research Institute ( http://www.idiap.ch/en ), where he heads the Biometrics Security and Privacy group ( http://www.idiap.ch/en/scientific-research/biometrics-security-and-privacy ) and conducts research on face recognition, speaker recognition, vein recognition and presentation attack detection (anti-spoofing). The Biometrics Security and Privacy group prioritises reproducibility in research and make freely available the signal-processing and machine-learning toolbox Bob ( https://www.idiap.ch/software/bob/ ) and the BEAT platform ( https://www.beat-eu.org/platform/ ).

He is lecturer at the Ecole Polytechnique Fédérale de Lausanne ( https://www.epfl.ch ) where he is teaching on “Fundamentals in Statistical Pattern Recognition” at the Doctoral School and the University of Lausanne where he is teaching on « Biometrics » in a Master program. He was VP Conferences of the IEEE Biometrics Council,  Associate Editor of IEEE Signal Processing Letters, Associate Editor of IEEE Transactions on Information Forensics and  Security, a Co-editor of the “Handbook of Biometric Anti-Spoofing”, a Guest Editor of the IEEE Transactions on Information Forensics and  Security Special Issue on “Biometric Spoofing and Countermeasures”, and Co-editor of the IEEE Signal Processing Magazine  Special  Issue on “Biometric Security and Privacy”. He was the principal investigator of international research projects including MOBIO ( EU FP7 Mobile Biometry — http://www.mobioproject.org ), TABULA RASA ( EU FP7 Trusted Biometrics under Spoofing Attacks — http://www.tabularasa-euproject.org ) and BEAT ( EU FP7 Biometrics Evaluation and Testing — https://www.beat-eu.org ).

Finally he is the Director of the Swiss Center for Biometrics Research and Testing ( http://www.biometrics-center.ch ) at Idiap.

Sébastien Marcel

Sébastien Marcel
Idiap and EPFL, Switzerland