IEM Seminar Series: An overview of 20 years of research in biometrics and recent work on template inversion from deep face embeddings
Event details
| Date | 22.05.2024 |
| Hour | 17:00 › 18:00 |
| Speaker | Prof. Sébastien Marcel, Head of the Biometrics Security and Privacy group, Idiap Research Institute |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Abstract
Biometrics refers to the automatic recognition of individuals based on their physiological and/or behavioural characteristics. This field of research encompasses many topics such as biometric recognition (face, voice, fingerprint, iris or vascular), vulnerability assessment or attack prevention (spoofing, deepfakes or morphing). Since most of these technologies are now AI-driven (e.g. face recognition is powered by large deep neural networks) it opens new challenges and research avenues. In this talk, we give an overview of 20 years of research in the field in our team. Then we focus on a recent impactful piece of work showing how deep face recognition embeddings can be inverted to reconstruct the face image hence putting the security and privacy of biometric data at risk.
Biography
Prof Sébastien Marcel (IEEE Senior member) is a senior researcher at the Idiap Research Institute (Switzerland), he heads the Biometrics Security and Privacy group and conducts research on face recognition, speaker recognition, vein recognition, attack detection (presentation attacks, morphing attacks, deepfakes) and template protection. He is also Professor at the University de Lausanne (UNIL) at the School of Criminal Justice and lecturer at the Ecole Polytechnique Fédérale de Lausanne (EPFL). He received his 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 also the Director of the Swiss Center for Biometrics Research and Testing, which conducts certifications of biometric products. He is Associate Editor of IEEE Transactions on Biometrics and Identity Science. He was Associate Editor of IEEE Signal Processing Letters, Associate Editor of IEEE Transactions on Information Forensics and Security, 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 is also the lead Editor of the Springer Handbook of Biometrics Anti-Spoofing (Editions 1, 2 and 3).
Biometrics refers to the automatic recognition of individuals based on their physiological and/or behavioural characteristics. This field of research encompasses many topics such as biometric recognition (face, voice, fingerprint, iris or vascular), vulnerability assessment or attack prevention (spoofing, deepfakes or morphing). Since most of these technologies are now AI-driven (e.g. face recognition is powered by large deep neural networks) it opens new challenges and research avenues. In this talk, we give an overview of 20 years of research in the field in our team. Then we focus on a recent impactful piece of work showing how deep face recognition embeddings can be inverted to reconstruct the face image hence putting the security and privacy of biometric data at risk.
Biography
Prof Sébastien Marcel (IEEE Senior member) is a senior researcher at the Idiap Research Institute (Switzerland), he heads the Biometrics Security and Privacy group and conducts research on face recognition, speaker recognition, vein recognition, attack detection (presentation attacks, morphing attacks, deepfakes) and template protection. He is also Professor at the University de Lausanne (UNIL) at the School of Criminal Justice and lecturer at the Ecole Polytechnique Fédérale de Lausanne (EPFL). He received his 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 also the Director of the Swiss Center for Biometrics Research and Testing, which conducts certifications of biometric products. He is Associate Editor of IEEE Transactions on Biometrics and Identity Science. He was Associate Editor of IEEE Signal Processing Letters, Associate Editor of IEEE Transactions on Information Forensics and Security, 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 is also the lead Editor of the Springer Handbook of Biometrics Anti-Spoofing (Editions 1, 2 and 3).
Practical information
- General public
- Free
Contact
- Christelle Pétremand