Searchable face recognition authentication based on homomorphic encryption

Abstract

Recent advances in deep learning-based facial recognition have sparked significant concerns over data security and privacy. To minimize storage and computational overhead, facial data is frequently outsourced to cloud servers for matching. Unlike passwords, facial features uniquely identify individuals, creating irreversible risks if compromised. Searchable Encryption (SE) schemes have emerged to protect outsourced data in the cloud, enabling queries directly over encrypted data. However, existing approaches primarily support deterministic exact match searches, neglecting the natural variability of facial features due to temporal and environmental factors, leading to decreased accuracy. Furthermore, reliance on symmetric encryption potentially compromises data confidentiality and integrity. To address these limitations, we propose SFRA, an efficient and verifiable Searchable Facial Recognition Authentication scheme. SFRA leverages locality-sensitive hashing combined with twin bloom filters to generate a tree-structured index storing encrypted facial feature vectors extracted by a deep learning model. During retrieval, the similarity between query trapdoors and stored index is measured using a predefined threshold for successful matching. We also define a comprehensive security framework and rigorously prove SFRA’s security under three leakage patterns. Empirical experiments in real-world datasets demonstrate that SFRA achieves superior accuracy and computational efficiency. Overall, SFRA significantly enhances security and efficiency in encrypted facial recognition systems for cloud deployments.