加密域人脸识别提速50倍，还能保持100%准确率
Privacy-preserving Preselection for Face Identification Based on Packing
- 用打包技术预筛选加密人脸模板，减少计算量
- 在LFW/CASIA数据集上300毫秒内查完1000个模板，准确率100%
- 适合需要高隐私保护的实时人脸识别场景
由于隐私担忧和原始人脸数据被恢复的风险，基于密文域的人脸识别系统受到广泛关注。然而，随着密文模板库规模增大，检索过程变得愈发耗时。为此，我们提出一种新型高效方案——基于打包的隐私保护人脸识别预筛选（PFIP）。该方案引入创新的预筛选机制以降低计算开销，并通过打包模块提升注册阶段生物特征系统的灵活性。在LFW和CASIA数据集上的大量实验表明，PFIP保持了原始人脸识别模型的准确性，在300毫秒内完成1000个密文人脸模板的检索，命中率达100%。相比现有方法，检索效率提升近50倍。
原文摘要 · Abstract (English)
Face identification systems operating in the ciphertext domain have garnered significant attention due to increasing privacy concerns and the potential recovery of original facial data. However, as the size of ciphertext template libraries grows, the face retrieval process becomes progressively more time-intensive. To address this challenge, we propose a novel and efficient scheme for face retrieval in the ciphertext domain, termed Privacy-Preserving Preselection for Face Identification Based on Packing (PFIP). PFIP incorporates an innovative preselection mechanism to reduce computational overhead and a packing module to enhance the flexibility of biometric systems during the enrollment stage. Extensive experiments conducted on the LFW and CASIA datasets demonstrate that PFIP preserves the accuracy of the original face recognition model, achieving a 100% hit rate while retrieving 1,000 ciphertext face templates within 300 milliseconds. Compared to existing approaches, PFIP achieves a nearly 50x improvement in retrieval efficiency.
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。