Towards Privacy-Preserving, Real-Time and Lossless Feature Matching

TL;DR

This paper introduces SecureVector, a novel feature protection module that enables real-time, lossless, and privacy-preserving feature matching using a combination of random permutations, 4L-DEC conversion, and homomorphic encryption, outperforming existing methods.

Contribution

SecureVector is the first approach to achieve real-time, lossless, and highly secure feature matching with privacy preservation, addressing limitations of prior transformation and cryptographic methods.

Findings

SecureVector achieves real-time, lossless feature matching.

It provides higher security levels than current state-of-the-art methods.

Extensive experiments validate its effectiveness across multiple applications.

Abstract

Most visual retrieval applications store feature vectors for downstream matching tasks. These vectors, from where user information can be spied out, will cause privacy leakage if not carefully protected. To mitigate privacy risks, current works primarily utilize non-invertible transformations or fully cryptographic algorithms. However, transformation-based methods usually fail to achieve satisfying matching performances while cryptosystems suffer from heavy computational overheads. In addition, secure levels of current methods should be improved to confront potential adversary attacks. To address these issues, this paper proposes a plug-in module called SecureVector that protects features by random permutations, 4L-DEC converting and existing homomorphic encryption techniques. For the first time, SecureVector achieves real-time and lossless feature matching among sanitized features, along with much higher security levels than current state-of-the-arts. Extensive experiments on face recognition, person re-identification, image retrieval, and privacy analyses demonstrate the effectiveness of our method. Given limited public projects in this field, codes of our method and implemented baselines are made open-source in https://github.com/IrvingMeng/SecureVector.