HE_FaceNet frame diagram.
<div><p>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 recognit...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , , , , , |
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852022805011365888 |
|---|---|
| author | Zhigang Song (113445) |
| author2 | Gong Wang (745924) Wenqin Yang (16536927) Yunliang Li (5664629) Yinsheng Yu (20707379) Zeli Wang (5508272) Xianghan Zheng (20707382) Yang Yang (45629) |
| author2_role | author author author author author author author |
| author_facet | Zhigang Song (113445) Gong Wang (745924) Wenqin Yang (16536927) Yunliang Li (5664629) Yinsheng Yu (20707379) Zeli Wang (5508272) Xianghan Zheng (20707382) Yang Yang (45629) |
| author_role | author |
| dc.creator.none.fl_str_mv | Zhigang Song (113445) Gong Wang (745924) Wenqin Yang (16536927) Yunliang Li (5664629) Yinsheng Yu (20707379) Zeli Wang (5508272) Xianghan Zheng (20707382) Yang Yang (45629) |
| dc.date.none.fl_str_mv | 2025-02-11T18:40:56Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0314656.g001 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/HE_FaceNet_frame_diagram_/28394024 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Molecular Biology Neuroscience Science Policy Plant Biology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified posed significant risks optimization scheme based grouping similar faces approximate homomorphic encryption face recognition based performance analysis indicates he_facenet ), aimed framework first utilizes facial recognition technology facial recognition process he_facenet framework final recognition facial data clustering analysis xlink "> widely adopted trained model significantly improved recent years preserving method practical applicability plaintext storage paper proposes paper introduces modern society information leakage consuming nature clustering algorithms |
| dc.title.none.fl_str_mv | HE_FaceNet frame diagram. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>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.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_8100bb8ee8ea375da2b08ad3155481fe |
| identifier_str_mv | 10.1371/journal.pone.0314656.g001 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28394024 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | HE_FaceNet frame diagram.Zhigang Song (113445)Gong Wang (745924)Wenqin Yang (16536927)Yunliang Li (5664629)Yinsheng Yu (20707379)Zeli Wang (5508272)Xianghan Zheng (20707382)Yang Yang (45629)Molecular BiologyNeuroscienceScience PolicyPlant BiologySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedposed significant risksoptimization scheme basedgrouping similar facesapproximate homomorphic encryptionface recognition basedperformance analysis indicateshe_facenet ), aimedframework first utilizesfacial recognition technologyfacial recognition processhe_facenet frameworkfinal recognitionfacial dataclustering analysisxlink ">widely adoptedtrained modelsignificantly improvedrecent yearspreserving methodpractical applicabilityplaintext storagepaper proposespaper introducesmodern societyinformation leakageconsuming natureclustering algorithms<div><p>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.</p></div>2025-02-11T18:40:56ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0314656.g001https://figshare.com/articles/figure/HE_FaceNet_frame_diagram_/28394024CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/283940242025-02-11T18:40:56Z |
| spellingShingle | HE_FaceNet frame diagram. Zhigang Song (113445) Molecular Biology Neuroscience Science Policy Plant Biology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified posed significant risks optimization scheme based grouping similar faces approximate homomorphic encryption face recognition based performance analysis indicates he_facenet ), aimed framework first utilizes facial recognition technology facial recognition process he_facenet framework final recognition facial data clustering analysis xlink "> widely adopted trained model significantly improved recent years preserving method practical applicability plaintext storage paper proposes paper introduces modern society information leakage consuming nature clustering algorithms |
| status_str | publishedVersion |
| title | HE_FaceNet frame diagram. |
| title_full | HE_FaceNet frame diagram. |
| title_fullStr | HE_FaceNet frame diagram. |
| title_full_unstemmed | HE_FaceNet frame diagram. |
| title_short | HE_FaceNet frame diagram. |
| title_sort | HE_FaceNet frame diagram. |
| topic | Molecular Biology Neuroscience Science Policy Plant Biology Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified posed significant risks optimization scheme based grouping similar faces approximate homomorphic encryption face recognition based performance analysis indicates he_facenet ), aimed framework first utilizes facial recognition technology facial recognition process he_facenet framework final recognition facial data clustering analysis xlink "> widely adopted trained model significantly improved recent years preserving method practical applicability plaintext storage paper proposes paper introduces modern society information leakage consuming nature clustering algorithms |