FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders

TL;DR

FaceMAE introduces a privacy-preserving face recognition framework using masked autoencoders that effectively balances privacy protection with recognition accuracy, outperforming previous methods on multiple datasets.

Contribution

The paper presents a novel FaceMAE framework that reconstructs faces from masked images to enhance privacy without sacrificing recognition performance.

Findings

Reconstructed images are difficult to retrieve identities, ensuring privacy.

FaceMAE reduces error rates by at least 50% on multiple face recognition benchmarks.

The method performs well on public face datasets like CASIA-WebFace and WebFace260M.

Abstract

Face recognition, as one of the most successful applications in artificial intelligence, has been widely used in security, administration, advertising, and healthcare. However, the privacy issues of public face datasets have attracted increasing attention in recent years. Previous works simply mask most areas of faces or synthesize samples using generative models to construct privacy-preserving face datasets, which overlooks the trade-off between privacy protection and data utility. In this paper, we propose a novel framework FaceMAE, where the face privacy and recognition performance are considered simultaneously. Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE. We tailor the instance relation matching (IRM) module to minimize the distribution gap between real faces and FaceMAE reconstructed ones. During the deployment phase, we use trained FaceMAE to reconstruct images from masked faces of unseen identities without extra training. The risk of privacy leakage is measured based on face retrieval between reconstructed and original datasets. Experiments prove that the identities of reconstructed images are difficult to be retrieved. We also perform sufficient privacy-preserving face recognition on several public face datasets (i.e. CASIA-WebFace and WebFace260M). Compared to previous state of the arts, FaceMAE consistently \textbf{reduces at least 50\% error rate} on LFW, CFP-FP and AgeDB.