Pura: An Efficient Privacy-Preserving Solution for Face Recognition

2025-05-21

AI Summary

To address privacy risks arising from the sensitivity of facial images, this paper proposes an efficient ciphertext-domain face recognition system. Methodologically, it introduces a non-interactive threshold Paillier homomorphic encryption framework, integrated with customized secure computation protocols for the ciphertext domain and parallelization optimizations, enabling end-to-end encrypted recognition without exposing plaintext features. The key contributions are: (i) the first deep integration of threshold Paillier encryption with parallel secure computation, eliminating interactive overhead and significantly improving ciphertext computational efficiency; and (ii) a formal security proof establishing strong privacy guarantees—namely, semantic security and collusion resistance. Experiments demonstrate that the system achieves 16× faster recognition than the state-of-the-art while preserving full accuracy. This work provides a practical, verifiable, and scalable solution for large-scale face recognition in privacy-sensitive applications.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Philosophy and Ethics of AI: Privacy & Security

Application Category

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

Abstract

Face recognition is an effective technology for identifying a target person by facial images. However, sensitive facial images raises privacy concerns. Although privacy-preserving face recognition is one of potential solutions, this solution neither fully addresses the privacy concerns nor is efficient enough. To this end, we propose an efficient privacy-preserving solution for face recognition, named Pura, which sufficiently protects facial privacy and supports face recognition over encrypted data efficiently. Specifically, we propose a privacy-preserving and non-interactive architecture for face recognition through the threshold Paillier cryptosystem. Additionally, we carefully design a suite of underlying secure computing protocols to enable efficient operations of face recognition over encrypted data directly. Furthermore, we introduce a parallel computing mechanism to enhance the performance of the proposed secure computing protocols. Privacy analysis demonstrates that Pura fully safeguards personal facial privacy. Experimental evaluations demonstrate that Pura achieves recognition speeds up to 16 times faster than the state-of-the-art.

Problem

• Enhance privacy in face recognition systems
• Improve efficiency of encrypted data processing
• Enable secure non-interactive face recognition

Innovation

• Uses threshold Paillier cryptosystem for privacy
• Designs secure protocols for encrypted data operations
• Introduces parallel computing to boost performance