Since his arrival at Idiap 20 years ago, Sébastien Marcel is shaking up the research community in biometry. After several major projects and a long term hard work, the researcher established the bases for a new biometrics standard.
Biometrics Security & Privacy
Biometrics refers to the automatic recognition of individuals based on their physiological and/or behavioral characteristics.
The Biometrics Security and Privacy (BSP) group at Idiap focuses on three main areas of research:
- Biometric recognition: We investigate and develop new biometrics based recognition algorithms, notably for face, voice, and vein biometric modalities.
- Presentation attack detection: We look for new and better ways of detecting presentation attacks on face, voice, and vein biometric recognition systems.
- Biometric template protection: We research effective methods of preserving both the security of biometric recognition systems and the privacy of their users by protecting the biometric models ("templates") that are employed by the system for recognition purposes.
The BSP group prioritizes reproducibility in research. This is important for ensuring that our work can be both verified and built upon by the wider research community. To enable reproducibility, we mainly make use of our Python-based signal-processing and machine-learning toolbox, Bob, which we make freely available for academic purposes. The group also develops and maintains the BEAT platform -- a MLaaS platform compliant with Swiss and European data-security norms.
The group participates in several large-scale biometrics projects at Swiss (SNSF), European (H2020) or world-wide levels (eg. IARPA/DARPA) but also conducts projects directly with companies.
The BSP group provides also expertise to the Swiss Center for Biometrics Research and Testing, which, among other things, carries out tests and evaluations on commercial products related to biometrics.
Group News
To face the increasing use of biometrics systems, Android set up its own certification standard. The biometrics center of Idiap became accredited to deliver certificates meeting these standards. This competence builds up on the FIDO accreditation obtained in 2019.
With one million Swiss francs budget and supported by the Innosuisse agency, the CANDY project will develop and patent a contact-less scanner allowing to identify people using the venous patterns of their hands. The project is a collaboration between the Global ID start-up and Idiap Research Institute.
The European Association for Biometrics organized its workshop at Idiap. European researchers and representatives from various companies gathered to discuss presentation attack detection.
In the face recognition research field, new challenges are going harder as the field limits are expanding. Tiago de Freitas Pereira award from the European Association for Biometrics is a significant recognition for his work during his thesis.
Group Job Openings
- Several Openings for Cross-Disciplinary Senior Researcher positions — by admin — last modified Mar 01, 2021
- With the growth of the institute, in addition to increased Federal funding to further support its activities, Idiap is opening several additional permanent senior research scientist positions.
Current Group Members

MARCEL, Sébastien
(Senior Researcher)
- website

KORSHUNOV, Pavel
(Research Associate)
- website

BHATTACHARJEE, Sushil (Kumar)
(Research Associate)
- website

GEISSBUHLER, David
(Research Associate)
- website

KRIVOKUCA, Vedrana
(Research Associate)
- website

GEORGE, Anjith
(Research Associate)
- website

MOHAMMADI, Amir
(Postdoctoral Researcher)
- website

DE FREITAS PEREIRA, Tiago
(Postdoctoral Researcher)
- website

KOTWAL, Ketan
(Postdoctoral Researcher)
- website

UNNERVIK, Alex
(Research Assistant)
- website

OTROSHI SHAHREZA, Hatef
(Research Assistant)
- website

COLBOIS, Laurent
(Research Assistant)
- website

ZHANG, Xinyi
(Master Student)

LINGHU, Yu
(Master Student)

SCHMIDLI, Dominic
(Master Student)

BROS, Victor
(Research Intern)
- website

JAIN, Anubhav
(Trainee)
- website
Alumni
- AEBERHARD, Niels
- ATANASOAEI, Constantin-Cosmin
- BALA SUBBURAMAN, Venkatesh
- BENDALE, Abhijit
- BOURLARD, Maxime
- CHINGOVSKA, Ivana
- DIEFENBAUGH, Jaden
- EGLITIS, Teodors
- EL KHOURY, Elie
- EL SHAFEY, Laurent
- ERDOGMUS, Nesli
- GALBALLY, Javier
- GÜNTHER, Manuel
- HALSTEAD, Michael (Allan)
- HEUSCH, Guillaume
- JOHANSSON, Niklas
- JUST, Agnès
- KEOMANY, Jean
- KOMATY, Alain
- MÄÄTTÄ, Jukka
- MANDASARI, Miranti
- MCCOOL, Christopher
- MCLAREN, Mitchell
- MEHTA, Rakesh
- MILLIUS, Josselin
- MILLIUS, Loris
- MOSTAANI, Zohreh
- NGUYEN, Huy (Hong)
- NIKISINS, Olegs
- ORRÙ, Giulia
- PETTINATO, Michela
- RABELLO DOS ANJOS, André
- ROY, Anindya
- SANCHEZ RIERA, Jordi
- SARFJOO, Saeed (Seyyed)
- SARKAR, Eklavya
- THURRE, Veronique
- TOME, Pedro
- VANONI, Matthias
- WALLACE, Roy (Geoffrey)
Active Research Grants
- ALLIES - Autonomous Lifelong learnIng intelLigent Systems
- BATL - Biometric Authentification with Timeless Learner
- CANDY - ContActless finger veiN recognition and presentation attack Detection on-the-flY
- HARDENING - HARDENING: Heterogeneous face recognition for unified identity management
- MARGIN - MARGIN: Multi-modal federated age verification
- NATAI - The Nature of Artificial Intelligence
- TRESPASS-ETN - TRaining in Secure and PrivAcy-preserving biometricS
Past Research Grants
- 3DFINGERVEIN - 3D FingerVein Biometrics
- ATAP - ATAP - Continuous Authentication Program
- BBC_BOB - Adapting bespoke speaker identification models to be used in IDIAP's 'Bob.Spear' speaker recognition software
- BBFOR2 - Bayesian Biometrics for Forensics
- BEAT - Biometrics Evaluation and Testing
- BIOWAVE - BIOWAVE pre-product, a BIOmetric Watch Activated by VEins
- COHFACE - COntactless Heartbeat detection for trustworthy FACE Biometrics
- CONTEXT - Context-based modelling for object detection
- CSSB - Centre Suisse en Sécurité Biométrique
- EMMA1 - Expression Mimics Marker Analysis
- FARGO - Convenient and Secure 3D Face Recognition based on RGB-D Cameras
- FEDARS - Feature Extraction from Deep learning Architectures for face Recognition Systems
- GOOGLE_MOBILE - Mobile Face and Voice Anti Spoofing
- HFACE - Heterogeneous Face Recognition
- LAB_FIDO - Création d'un laboratoire de test biométrique agréé
- LOBI - Low Complexity Binary Features for Robust-to-Noise Speaker Recognition
- MOBIO - Mobile Biometry
- ODESSA - Online Diarization Enhanced by recent Speaker identification and Sequential learning Approaches
- REPLAY - Face Authentication Robust to Replay Attacks
- SAVI - Spotting Audio-Visual Inconsistencies
- SWAN - Secure Access Control over Wide Area Network
- TABULARASA - Trusted Biometrics under Spoofing Attacks
- TESLA - An Adaptive Trust-based e-assesment System for Learning
- VERIFAKE - Vulnerability assessment and detection of Deepfake videos