Modern face recognition systems utilize deep neural networks to extract salient features from a face. These features denote embeddings in latent space and are often stored as templates in a face recognition system. These embeddings are susceptible to data leakage and, in some cases, can even be used to reconstruct the original face image. To prevent compromising identities, template protection schemes are commonly employed. However, these schemes may still not prevent the leakage of soft biometric information such as age, gender and race. To alleviate this issue, we propose a novel technique that combines Fully Homomorphic Encryption (FHE) with an existing template protection scheme known as PolyProtect. We show that the embeddings can be compressed and encrypted using FHE and transformed into a secure PolyProtect template using polynomial transformation, for additional protection. We demonstrate the efficacy of the proposed approach through extensive experiments on multiple datasets. Our proposed approach ensures irreversibility and unlinkability, effectively preventing the leakage of soft biometric attributes from face embeddings without compromising recognition accuracy.

翻译：现代人脸识别系统利用深度神经网络从人脸中提取显著特征。这些特征表示潜在空间中的嵌入向量，通常作为模板存储在人脸识别系统中。此类嵌入向量容易遭受数据泄露，在某些情况下甚至可被用于重建原始人脸图像。为防止身份信息被泄露，通常采用模板保护方案。然而，这些方案仍可能无法阻止年龄、性别、种族等软生物特征信息的泄露。为解决这一问题，我们提出了一种新技术，将全同态加密（FHE）与现有模板保护方案PolyProtect相结合。研究表明，嵌入向量可通过全同态加密进行压缩与加密，并经由多项式变换转换为安全的PolyProtect模板，从而提供额外保护。通过在多个数据集上的大量实验，我们验证了所提方法的有效性。该方法确保了不可逆性与不可关联性，在不影响识别精度的前提下，有效防止了人脸嵌入向量中软生物特征属性的泄露。