通过函数秘密共享实现的鲁棒肤色驱动隐私保护人脸识别
Robust Skin Color Driven Privacy Preserving Face Recognition via Function Secret Sharing
AI总结:
本研究针对现有隐私保护人脸识别的性能与安全缺陷,引入肤色特征辅助训练,并提出基于函数秘密共享的嵌入比较协议,兼具鲁棒性与更高的计算效率。
摘要:
在本研究中,我们利用人脸图像中的纯肤色块作为额外信息,并行训练辅助肤色特征提取器与人脸识别模型,以提升当前最优(SOTA)隐私保护人脸识别(PPFR,Privacy Preserving Face Recognition)系统的性能。我们的方案对黑盒攻击以及成熟的基于生成对抗网络(GAN,Generative Adversarial Network)的图像恢复具有鲁棒性。我们分析了以往研究中的潜在风险:其提出的余弦相似度计算可能直接泄露存储在服务端的受保护预计算嵌入。我们提出了一种基于函数秘密共享(FSS,Function Secret Sharing)的人脸嵌入比较协议,不会泄露任何中间结果。此外,实验表明,与基于秘密共享(SS,Secret Sharing)的协议相比,所提协议效率更高。
英文摘要:
In this work, we leverage the pure skin color patch from the face image as the additional information to train an auxiliary skin color feature extractor and face recognition model in parallel to improve performance of state-of-the-art (SOTA) privacy-preserving face recognition (PPFR) systems. Our solution is robust against black-box attacking and well-established generative adversarial network (GAN) based image restoration. We analyze the potential risk in previous work, where the proposed cosine similarity computation might directly leak the protected precomputed embedding stored on the server side. We propose a Function Secret Sharing (FSS) based face embedding comparison protocol without any intermediate result leakage. In addition, we show in experiments that the proposed protocol is more efficient compared to the Secret Sharing (SS) based protocol.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。