European Biometrics Awards 2020

On 16 September 2020 the European Association for Biometrics (EAB) awarded young researchers for their outstanding works in the area of biometrics. An international jury chose 3 candidates out of a broad range of submitted high quality papers to present their significant contribution in front of the jury, the EAB members and the public audience in a virtual meeting.

Winner of the Max Snijder Award Dr. Andreas Nautsch during the presentation of his Work

European Biometric Max Snijder Award

In 2020 for the second time the EAB Max Snijder Award is granted to a researcher, who expressed through his work a wider perspective to get a broader picture on biometric applications. The winner of this award is Andreas Nautsch, who who conducted his PhD project at Hochschule Darmstadt/TechnicalUniversity of Darmstadt (Germany), and presented the topic of Security & Privacy in Voice Biometrics and Beyond. A holistic perspective was presented for: better decision making compensating for changing signal quality; voice presentation attack detection; privacy-preserving likelihood ratio computation using Paillier homomorphic encryption and secure two-party computation, and the interrelation of performance evaluation paradigms in biometrics standardisation and forensic sciences. These, whilst directly leading to new metrics in international research challenges on security and on privacy for speech data, are also put in the bigger picture: interdisciplinary research including speech, legal, cryptography and biometric experts.

The winner of the EAB Industry Award 2020 Dr Philipp Terhörst being interviewed by Prof Patrizio Campisi and Prof Raymond Veldhuis

European Biometric Industry Award

This year the European Biometrics Industry Award goes to Philipp Terhörst from Fraunhofer IGD, (Germany) for his work Mitigating Soft-Biometric driven Bias and Privacy Concerns in Face Recognition Systems. During the final he focused on high-performance of current face recognition systems is driven by the advances in extracting deeply-learned feature representations of face images. However, the success of these templates came at the cost of two major discriminatory concerns: First, many biometric solutions are built on representation-learning strategies that optimize total recognition performance. This often leads to a discriminatory recognition performance depended on the user's demographics. Second, the deeply-learned template of an individual contains more information than the individual's identity, such demographics and health status. Since for many applications, the templates are expected to be used for recognition only, this raises major privacy issues. This work analyses these problems and proposes easily-integrable solutions to effectively mitigate both concerns.

With his outstanding presentation during the introduction to their works, Philipp Terhörst was also awarded the Best Presentation Award.