Make Privacy Renewable! Generating Privacy-Preserving Faces Supporting Cancelable Biometric Recognition

Tao Wang, Yushu Zhang, Xiangli Xiao, Lin Yuan, Zhihua Xia, Jian Weng

Abstract: The significant advancement in face recognition drives face privacy protection into a prominent research direction. Unlike de-identification, a recent class of face privacy protection schemes preserves identifiable formation for face recognition. However, these schemes fail to support the revocation of the leaked identity, causing attackers to potentially identify individuals and then pose security threats. In this paper, we explore the possibility of generating privacy-preserving faces (not features) supporting cancelable biometric recognition. Specifically, we propose a cancelable face generator (CanFG), which removes the physical identity for privacy protection and embeds the virtual identity for face recognition. Particularly, when leaked, the virtual identity can be revoked and renew as another one, preventing re-identification from attackers. Benefiting from the designed distance-preserving identity transformation, CanFG can guarantee separability and preserve recognizability of virtual identities. Moreover, to make CanFG lightweight, we design a simple but effective training strategy, which allows CanFG to require only one (rather than two) network for achieving stable multi-objective learning. Extensive experimental results and sufficient security analyses demonstrate the ability of CanFG to effectively protect physical identity and support cancelable biometric recognition. Our code is available at https://github.com/daizigege/CanFG.

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Systems] Systems and Middleware

Relevance To Conference:

As one of the important multimedia data, face data contains identity information that involves both privacy and usability, which are difficult to trade-off. This paper proposes a privacy-preserving face generator， which can protect face data well. The main contributions are as follows：

1. Our work supports cancelable face recognition, which allows revoking a leaked identity and renewing it as another one.

2. Our work provides a new training strategy to achieve privacy and usability simultaneously, which contributes to the healthy use of face data in many scenarios, especially for surveillance video.

3. Our work preserves more attributes including the background, and therefore can process multimedia data including images and videos.

Submission Number: 1595