文献类型：期刊文献

英文题名：Privacy-preserving method for face recognition based on homomorphic encryption

作者：Song, Zhigang[1];Wang, Gong[2];Yang, Wenqin[1];Li, Yunliang[2];Yu, Yinsheng[2];Wang, Zeli[3];Zheng, Xianghan[2];Yang, Yang[4]

机构：[1]Acad Digital China, Fuzhou, Fujian, Peoples R China;[2]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou, Fujian, Peoples R China;[3]East China Univ Sci & Technol, Sch Business, Shanghai, Peoples R China;[4]Singapore Management Univ, Sch Comp & Informat Syst, Singapore, Singapore

年份：2025

卷号：20

期号：2

外文期刊名：PLOS ONE

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001418839600062)】；

基金：This work is supported by National Natural Science Foundation of China under Grant No. 62372110 awarded to Y.Y8. and X.Z, Fujian Provincial Natural Science Foundation under Grant 2023J02008 awarded to Y.Y8. and X.Z, and Regional Development Project of Fujian Provincial Department of Science and Technology under Grant No. 2023H4007 awarded to Z.W.

语种：英文

摘要：In recent years, facial recognition technology has been widely adopted in modern society. However, the plaintext storage, computation, and transmission of facial data have posed significant risks of information leakage. To address this issue, this paper proposes a facial recognition framework based on approximate homomorphic encryption (HE_FaceNet), aimed at effectively mitigating privacy leaks during the facial recognition process. The framework first utilizes a pre-trained model to extract facial feature templates, which are then encrypted. The encrypted templates are matched using Euclidean distance, with the final recognition being performed after decryption. However, the time-consuming nature of homomorphic encryption calculations limits the practical applicability of the HE_FaceNet framework. To overcome this limitation, this paper introduces an optimization scheme based on clustering algorithms to accelerate the facial recognition process within the HE_FaceNet framework. By grouping similar faces into clusters through clustering analysis, the efficiency of searching encrypted feature values is significantly improved. Performance analysis indicates that the HE_FaceNet framework successfully protects facial data privacy while maintaining high recognition accuracy, and the optimization scheme demonstrates high accuracy and significant computational efficiency across facial datasets of varying sizes.