IAPR/IEEE Winter School on Biometrics 2021

Biometric Presentation Attack Detection

Slides (pdf)  Size: 48.1MB


In biometrics, Presentation Attacks (PA also referred to as spoofing) are performed by falsifying the biometric trait and then presenting this falsified information to the biometric system, one such example is to fool a fingerprint system by copying the fingerprint of another person and creating an artificial or gummy finger which can then be presented to the biometric system to falsely gain access. This is an issue that needs to be addressed because it has recently been shown that conventional biometric techniques are vulnerable to presentation attacks. One of the main challenges in Presentation Attack Detection (PAD also referred to as anti-spoofing) is to find a set of features and models (mostly classifiers) that allows systems to effectively distinguish signals that were directly emitted by a human from those reproduced by an attacker. This talk will give an introduction to the field, present a range of PAs and PAD techniques with a focus on the face modality.


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