ANR-DFG 2018 French-German calls for joint projects in Natural, Life and Engineering Sciences
RESPECT
reliable, secure and privacy preserving multi-biometric person authentication
Hochschule Darmstadt (Germany)
The biometrics and internet security research group da/sec Hochschule Darmstadt was established in 2008, when the CASED center was founded. The focus of the group is on highly innovative and applied IT security research in the special fields of biometrics and digital forensics. The group is funded by various national and international projects (see http://www.christoph-busch.de/projects.html for an overview) and closely cooperating with the partners in theNational Center for Applied Cybersecurity ATHENE https://www.athene-center.de/), which was established as follow-up of CRISP and CASED. In addition, the da/sec research lab is an active member in the European Association for Biometrics (EAB), and organizer of several international conferences on Biometrics such as the IEEE BIOSIG conference and the EAB-RPC conference. We also contribute to the international standardization in the field within the ISO/IEC JTC1 SC37. Our biometric research is covering various physiological and behavioural biometrics including presentation attack detection and biometric template protection for the characteristics fingerprint, vein, iris, ear, 2D- and 3D-face, speaker and signature recognition. Furthermore we focus on privacy enhancing technologies such as biometric template protection and integration in physical and logical access control.
Prof. Dr. Christoph Busch
Principal investigator
Lázaro Janier González-Soler
Ph.D. student
Hochschule Ansbach (Germany)
The Hochschule Ansbach https://www.hs-ansbach.de/en/home/ is a young, modern Bavarian University for Applied Sciences with a focus on technology, business, and media. Within the broader IT-security and data privacy research fields, our contributions lie on secure and privacy-friendly biometric recognition. We are an active member in the European Association for Biometrics (EAB), and organise several international conferences on Biometrics such as the IEEE BIOSIG conference. We also contribute to the international standardization in the field within the ISO/IEC JTC1 SC37. Our research work focuses on generalisable and explainable presentation attack detection and biometric template protection methods for various biometric characteristics (e.g., face, iris, fingerprint, handwritten signature, or speaker). As a University for Applied Sciences, the application dimension of the research plays a central role for us - we work towards integration of biometrics in physical and logical access control, and on the use of biometrics for forensic purposes.
Prof. Dr. Marta Gomez-Barrero
Principal investigator
EURECOM (France)
EURECOM is a private, graduate engineering school and research centre. Its mission
is to provide graduate training and to undertake internationally leading research within its three principle
domains of specialisation: Communications Systems; Digital Security and Data Science. The research within
RESPECT will be conducted within the Audio Security and Privacy Research Group, part of the Biometrics and Digital Media Research Group in the Digital Security
Department. The group’s research interests include: forensics; speaker recognition; face recognition; soft
biometrics; surveillance; privacy, and digital signal processing. It maintains close relationships with industry (currently
Intel Mobile Communications, NXP Software, STMicroelectronics and Orange) and has participated in several past and ongoing European collaborative
projects in topics related to RESPECT and has played a pivotal role in the organisation of several competitive
evaluations, the most recent of which, ASVspoof, aimed to advance the state of the art in spoofing countermeasures
for automatic speaker verification. EURECOM’s most recent expertise relevant to this project includes the
design of novel techniques to preserve privacy in biometric voice authentication systems, new spoofing countermeasures for speaker recognition, speaker diarization/indexing (recognition of multiple/
competing speakers), novel approaches to linguistic normalisation for speaker diarization, soft biometrics,
surveillance, evasion and short-duration speaker recognition.
Prof. Dr. Massimiliano Todisco
Principal investigator
Dr. Madhu Kamble
Post-doc
Prof. Dr. Nicholas Evans
Co-Principal investigator
Inria (France)
Inria (National Institute for Research in Computer Science and Control) is a French
public sector scientific and technological institute operating under the dual authority of the Ministry of Research
and the Ministry of Industry. INRIA’s missions are ”to undertake basic and applied research, to design experimental
systems, to ensure technology and knowledge transfer, to organize international scientific exchanges, to carry out
scientific assessments, and to contribute to standardization”. The research carried out at INRIA brings together
experts from the fields of computer science and applied mathematics covering the following areas: Networks
and Systems; Software Engineering and Symbolic Computing; Man-Machine Interaction; Image Processing, Data
Management, Knowledge Systems, Simulation and Optimization of Complex Systems.
The research within RESPECT will be conducted within the STARS (Spatio-Temporal Activity Recognition Systems)
research team, focused on the design of cognitive vision systems for Activity Recognition. More precisely,
STARS is interested in the real-time semantic interpretation of dynamic scenes observed by video cameras and
other sensors, studying long-term spatio-temporal activities performed by agents such as human beings, animals
or vehicles in the physical world. The major issue in semantic interpretation of dynamic scenes is to bridge the
gap between the subjective interpretation of data and the objective measures provided by sensors. To address this
problem STARS develops new techniques in the field of cognitive vision and cognitive systems for physical object
detection, activity understanding, activity learning, vision system design and evaluation. The expertise of STARS
related to the project includes soft biometrics, cosmetics induced spoofing, behavioral analysis.