TU Darmstadt / ULB / TUbiblio

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

Terhorst, Philipp ; Fahrmann, Daniel ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan (2020):
Beyond Identity: What Information Is Stored in Biometric Face Templates?
IEEE, 2020 IEEE International Joint Conference on Biometrics (IJCB), virtual Conference, 28.09.-01.10.2020, ISBN 978-1-7281-9186-7,
DOI: 10.1109/IJCB48548.2020.9304874,
[Conference or Workshop Item]

Abstract

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.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Terhorst, Philipp ; Fahrmann, Daniel ; Damer, Naser ; Kirchbuchner, Florian ; Kuijper, Arjan
Title: Beyond Identity: What Information Is Stored in Biometric Face Templates?
Language: English
Abstract:

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.

Publisher: IEEE
ISBN: 978-1-7281-9186-7
Uncontrolled Keywords: Biometrics, Machine learning, Artificial intelligence (AI), Face recognition
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 2020 IEEE International Joint Conference on Biometrics (IJCB)
Event Location: virtual Conference
Event Dates: 28.09.-01.10.2020
Date Deposited: 01 Feb 2021 08:09
DOI: 10.1109/IJCB48548.2020.9304874
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details