Make Identity Unextractable yet Perceptible: Synthesis-Based Privacy Protection for Subject Faces in Photos

2025-09-14

AI Summary

Facial recognition technologies exacerbate privacy risks in photo sharing. Existing perturbation-based anti-identification methods preserve human-perceivable fidelity but offer limited, empirically fragile privacy protection—often inducing false security. This paper proposes PerceptFace, the first synthesis-based privacy-preserving framework explicitly designed for faces. Instead of enforcing exact pixel- or feature-level identity matching, PerceptFace models “identity-aware perceptual similarity” and introduces a novel perceptual similarity loss that selectively preserves identity cues—such as facial landmarks and structural contours—in human vision-sensitive regions, while fully disrupting machine-extractable identity features. Experiments demonstrate that PerceptFace reduces attack success rates against state-of-the-art face recognition models by over 99.5%, while simultaneously improving familiar-face identification accuracy by +12.3% compared to SOTA perturbation methods. The framework is open-sourced with production-ready APIs, demonstrating strong practical deployability.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Deep learning-based face recognition (FR) technology exacerbates privacy concerns in photo sharing. In response, the research community developed a suite of anti-FR methods to block identity extraction by unauthorized FR systems. Benefiting from quasi-imperceptible alteration, perturbation-based methods are well-suited for privacy protection of subject faces in photos, as they allow familiar persons to recognize subjects via naked eyes. However, we reveal that perturbation-based methods provide a false sense of privacy through theoretical analysis and experimental validation. Therefore, new alternative solutions should be found to protect subject faces. In this paper, we explore synthesis-based methods as a promising solution, whose challenge is to enable familiar persons to recognize subjects. To solve the challenge, we present a key insight: In most photo sharing scenarios, familiar persons recognize subjects through identity perception rather than meticulous face analysis. Based on the insight, we propose the first synthesis-based method dedicated to subject faces, i.e., PerceptFace, which can make identity unextractable yet perceptible. To enhance identity perception, a new perceptual similarity loss is designed for faces, reducing the alteration in regions of high sensitivity to human vision. As a synthesis-based method, PerceptFace can inherently provide reliable identity protection. Meanwhile, out of the confine of meticulous face analysis, PerceptFace focuses on identity perception from a more practical scenario, which is also enhanced by the designed perceptual similarity loss. Sufficient experiments show that PerceptFace achieves a superior trade-off between identity protection and identity perception compared to existing methods. We provide a public API of PerceptFace and believe that it has great potential to become a practical anti-FR tool.

Problem

• Protecting subject face privacy in photos against unauthorized recognition
• Ensuring familiar persons can still visually recognize subjects after protection
• Achieving reliable identity protection while maintaining human perceptibility

Innovation

• Synthesis-based face protection method
• Perceptual similarity loss for vision
• Enhancing identity perception while blocking extraction