Personalized Face Privacy Protection From a Single Image

2026-05-18

AI Summary

This work addresses the growing threat to personal privacy posed by unauthorized scraping of online facial images for malicious facial recognition. To counter this, the authors propose FaceCloak, a system that generates lightweight, identity-specific, and generalizable privacy-preserving masks from a single user image. FaceCloak employs a three-stage perturbation learning strategy—synthetic image generation, iterative perturbation optimization, and manipulation in the identity embedding space—to selectively disrupt critical identity-discriminative regions. Extensive experiments across three benchmark datasets and ten state-of-the-art face recognition models demonstrate that FaceCloak substantially outperforms 29 existing privacy protection methods, effectively degrading recognition accuracy while preserving high visual fidelity of the protected images.

Abstract

Photos of faces uploaded online are vulnerable to malicious actors who can scrape facial images from online sources and intrude on personal privacy via unauthorized use of facial recognition models. This paper presents FaceCloak, a novel personalized face privacy protection system, which can generate defensive identity-specific universal face privacy masks from a single image of a user, causing facial recognition to fail. FaceCloak introduces a three-stage personalized face perturbation learning methodology: (1) It generates a small set of high-variety synthetic face images of a person based on a single image of the person. (2) It learns face cloaking by adding more protection to key facial-identity leakage regions through iterative perturbation generation over the small set of synthetic images, effectively shifting a user's identity embedding towards a distant anchor identity and away from a similar one. (3) It generates a personalized identity-protective mask in the form of pixel-wise cloaking, which is light-weight and can be efficiently applied to any facial image of a user while maintaining good perceptual quality. Extensive experiments on three popular face datasets across ten recognition models show the effectiveness of FaceCloak compared to 29 other existing representative methods. Code is available at https://github.com/zacharyyahn/FaceCloak

Problem

• face privacy
• personalized protection
• facial recognition
• identity leakage
• privacy-preserving

Innovation

• personalized face privacy
• universal adversarial perturbation
• identity-specific cloaking
• single-image synthesis
• face recognition evasion