用可撤销的量化方法实现高效安全的人脸检索。
Secure and Scalable Face Retrieval via Cancelable Product Quantization
- 分两阶段设计：快速过滤+加密精确排序
- 在多个数据集上兼顾精度与速度，支持实时应用
- 适合需要隐私保护的实时人脸识别系统
尽管现代人脸检索系统广泛应用，其检索阶段常外包给第三方，严重威胁用户肖像隐私。虽然同态加密（HE）能在密文空间进行计算，提供强安全保障，但其高计算开销使其难以用于实时场景。为此，我们提出可撤销产品量化（Cancelable Product Quantization），一种高效的安全人脸表示检索框架。该框架采用分层两阶段设计：(i) 高吞吐量的可撤销PQ索引模块，用于快速候选过滤；(ii) 细粒度的密文空间检索模块，用于最终精准排名。针对索引模块设计了定制化保护机制，既保障可撤销生物认证安全，又确保效率。在基准数据集上的实验表明，本方法在有效性、效率和安全性之间实现了良好平衡。
原文摘要 · Abstract (English)
Despite the ubiquity of modern face retrieval systems, their retrieval stage is often outsourced to third-party entities, posing significant risks to user portrait privacy. Although homomorphic encryption (HE) offers strong security guarantees by enabling arithmetic computations in the cipher space, its high computational inefficiency makes it unsuitable for real-time, real-world applications. To address this issue, we propose Cancelable Product Quantization, a highly efficient framework for secure face representation retrieval. Our hierarchical two-stage framework comprises: (i) a high-throughput cancelable PQ indexing module for fast candidate filtering, and (ii) a fine-grained cipher-space retrieval module for final precise face ranking. A tailored protection mechanism is designed to secure the indexing module for cancelable biometric authentication while ensuring efficiency. Experiments on benchmark datasets demonstrate that our method achieves an decent balance between effectiveness, efficiency and security.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。