Privacy-preserving method for face recognition based on homomorphic encryption.

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhigang Song, Gong Wang, Wenqin Yang, Yunliang Li, Yinsheng Yu, Zeli Wang, Xianghan Zheng, Yang Yang
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0314656
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144390120472576
author Zhigang Song
Gong Wang
Wenqin Yang
Yunliang Li
Yinsheng Yu
Zeli Wang
Xianghan Zheng
Yang Yang
author_facet Zhigang Song
Gong Wang
Wenqin Yang
Yunliang Li
Yinsheng Yu
Zeli Wang
Xianghan Zheng
Yang Yang
author_sort Zhigang Song
collection DOAJ
description 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.
format Article
id doaj-art-db6fa260c7244855bde7faab7c54ab07
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-db6fa260c7244855bde7faab7c54ab072025-08-20T02:28:23ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01202e031465610.1371/journal.pone.0314656Privacy-preserving method for face recognition based on homomorphic encryption.Zhigang SongGong WangWenqin YangYunliang LiYinsheng YuZeli WangXianghan ZhengYang YangIn 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.https://doi.org/10.1371/journal.pone.0314656
spellingShingle Zhigang Song
Gong Wang
Wenqin Yang
Yunliang Li
Yinsheng Yu
Zeli Wang
Xianghan Zheng
Yang Yang
Privacy-preserving method for face recognition based on homomorphic encryption.
PLoS ONE
title Privacy-preserving method for face recognition based on homomorphic encryption.
title_full Privacy-preserving method for face recognition based on homomorphic encryption.
title_fullStr Privacy-preserving method for face recognition based on homomorphic encryption.
title_full_unstemmed Privacy-preserving method for face recognition based on homomorphic encryption.
title_short Privacy-preserving method for face recognition based on homomorphic encryption.
title_sort privacy preserving method for face recognition based on homomorphic encryption
url https://doi.org/10.1371/journal.pone.0314656
work_keys_str_mv AT zhigangsong privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT gongwang privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT wenqinyang privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT yunliangli privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT yinshengyu privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT zeliwang privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT xianghanzheng privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption
AT yangyang privacypreservingmethodforfacerecognitionbasedonhomomorphicencryption