Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Learning Privacy-Enhancing Face Representations through Feature Disentanglement

: Bortolato, Blaz; Ivanovska, Marija; Rot, Peter; Križaj, Janez; Terhörst, Philipp; Damer, Naser; Peer, Peter; Struc, Vitomir


Štruc, V. ; Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
15th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2020. Proceedings : Buenos Aires, Argentina, 16-20 November 2020, Virtual
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-3080-4
ISBN: 978-1-7281-3079-8
International Conference on Automatic Face and Gesture Recognition (FG) <15, 2020, Online>
Fraunhofer IGD ()
Lead Topic: Smart City; Lead Topic: Visual Computing as a Service; Research Line: Computer vision (CV); Research Line: Human computer interaction (HCI); biometrics; face recognition; privacy enhancing technologies

Convolutional Neural Networks (CNNs) are today the de-facto standard for extracting compact and discriminative face representations (templates) from images in automatic face recognition systems. Due to the characteristics of CNN models, the generated representations typically encode a multitude of information ranging from identity to soft-biometric attributes, such as age, gender or ethnicity. However, since these representations were computed for the purpose of identity recognition only, the soft-biometric information contained in the templates represents a serious privacy risk. To mitigate this problem, we present in this paper a privacy-enhancing approach capable of suppressing potentially sensitive soft-biometric information in face representations without significantly compromising identity information. Specifically, we introduce a Privacy-Enhancing Face-Representation learning Network (PFRNet) that disentangles identity from attribute information in face representations and consequently allows to efficiently suppress soft-biometrics in face templates. We demonstrate the feasibility of PFRNet on the problem of gender suppression and show through rigorous experiments on the CelebA, Labeled Faces in the Wild (LFW) and Adience datasets that the proposed disentanglement-based approach is highly effective and improves significantly on the existing state-of-the-art.