Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Beyond Identity: What Information is Stored in Biometric Face Templates?

: Terhörst, Philipp; Fährmann, Daniel; Damer, Naser; Kirchbuchner, Florian; Kuijper, Arjan


Kakadiaris, Ioannis A. (General Chairs) ; Institute of Electrical and Electronics Engineers -IEEE-; Institute of Electrical and Electronics Engineers -IEEE-, Biometrics Council:
IEEE International Joint Conference on Biometrics, IJCB 2020 : 28 Sept.-1 Oct. 2020, Houston, Texas, Online
Piscataway, NJ: IEEE, 2020
ISBN: 978-1-7281-9186-7
ISBN: 978-1-7281-9187-4
10 S.
International Joint Conference on Biometrics (IJCB) <2020, Online>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Fraunhofer IGD ()
ATHENE; CRISP; Lead Topic: Visual Computing as a Service; Research Line: Computer vision (CV); biometrics; machine learning; artificial intelligence (AI); face recognition

Deeply-learned face representations enable the success of current face recognition systems. Despite the ability of these representations to encode the identity of an individual, recent works have shown that more information is stored within, such as demographics, image characteristics, and social traits. This threatens the user's privacy, since for many applications these templates are expected to be solely used for recognition purposes. Knowing the encoded information in face templates helps to develop bias-mitigating and privacy-preserving face recognition technologies. This work aims to support the development of these two branches by analysing face templates regarding 113 attributes. Experiments were conducted on two publicly available face embeddings. For evaluating the predictability of the attributes, we trained a massive attribute classifier that is additionally able to accurately state its prediction confidence. This allows us to make more sophisticated statements about the attribute predictability. The results demonstrate that up to 74 attributes can be accurately predicted from face templates. Especially non-permanent attributes, such as age, hairstyles, haircolors, beards, and various accessories, found to be easily-predictable. Since face recognition systems aim to be robust against these variations, future research might build on this work to develop more understandable privacy preserving solutions and build robust and fair face templates.