一种基于CKKS同态加密与神经网络的安全人脸识别方案

兰州理工大学学报 ›› 2023, Vol. 49 ›› Issue (2): 103-109.

• 自动化技术与计算机技术 • 上一篇下一篇

一种基于CKKS同态加密与神经网络的安全人脸识别方案

苏昀暄^1,2, 涂正^1,2, 王绪安^*1,2, 林川¹

1.武警工程大学网络与信息安全武警部队重点实验室, 陕西西安 710086;
2.贵州大学贵州公共大数据国家重点实验室, 贵州贵阳 550000

收稿日期:2021-09-27 出版日期:2023-04-28 发布日期:2023-05-05
通讯作者: 王绪安(1981-),男,湖北公安人,博士,教授.Email:wangxazjd@163.com
基金资助:
国家自然科学基金(61772550),贵州省公共大数据重点实验室开放课题基金(2019BDFKJJ008)

A secure face recognition scheme based on CKKS homomorphic encryption and neural network

SU Yun-xuan^1,2, TU Zheng^1,2, WANG Xu-an^1,2, LIN Chuan¹

1. Key Laboratory for Network and Information Security of the PAP, Engineering University of the PAP, Xi’an 710086, China;
2. The Foundation of Guizhou Provincial Key Laboratory of Public Big Data, Guizhou University, Guiyang 550000, China

Received:2021-09-27 Online:2023-04-28 Published:2023-05-05

摘要/Abstract

摘要： 随着大数据技术的不断发展,人脸识别应用越来越广泛,但随之而来的是用户隐私数据泄露等安全问题.针对此,提出一种在云服务器下基于同态加密与神经网络的人脸识别方案.通过CKKS同态加密方案对人脸图像进行加密,在云服务器中通过ResNet50 Model与Arcface Loss函数对LFW数据集进行训练,计算加密图片之间的向量相关性,对密文结果解密并比较阈值判断是否为同一个人,实现人脸识别.实验结果表明,该方案在LFW数据集上,阈值大约为0.25时,密文中的识别准确率达到99.398%,证明本文方案具有较高的识别精度.

关键词: 云计算, 人脸识别, 同态加密, 神经网络

Abstract: As big data technology has been evolving over the years, facial recognition is widely used in different fields. However, users are then troubled by safety problems, such as privacy disclosure and data leakage. A face recognition scheme based on homomorphic encryption and neural network under the cloud server is proposed in this paper. The face image is encrypted through the CKKS homomorphic encryption scheme, and the LFW data set is trained through the ResNet50 model and Arcface Loss function in the cloud server, then the vector correlation between the encrypted images is calculated, followed by the decryption of the ciphertext result and comparison with the threshold to judge whether it is the same person, to realize face recognition. The experiment result shows that on the LFW dataset, the scheme of this paper can recognize the cryptograph with an accuracy rate of 99.398% when the threshold value is about 0.25. This result proves the proposed scheme has high recognition accuracy.

Key words: cloud computing, face recognition, homomorphic encryption, neural network

中图分类号:

TP391

苏昀暄, 涂正, 王绪安, 林川. 一种基于CKKS同态加密与神经网络的安全人脸识别方案[J]. 兰州理工大学学报, 2023, 49(2): 103-109.

SU Yun-xuan, TU Zheng, WANG Xu-an, LIN Chuan. A secure face recognition scheme based on CKKS homomorphic encryption and neural network[J]. Journal of Lanzhou University of Technology, 2023, 49(2): 103-109.

参考文献

[1] SAID E,NASR M.Face recognition system [J].International Journal of Advanced Networking and Applications,2020,12(2):4567-4564.
[2] CHEON J H,KIM A,KIM M,et al.Homomorphic encryption for arithmetic of approximate numbers [C]//International Conference on the Theory and Application of Cryptology and Information Security.Cham:Springer,2017:409-437.
[3] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE,2016:770-778.
[4] DENG J,GUO J,XUE N,et al.ArcFace:additive angular margin loss for deep face recognition [C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach:IEEE,2019:4685-4694.
[5] JAURO F,CHIROMA H,GITAL A Y,et al.Deep learning architectures in emerging cloud computing architectures:Recent development,challenges and next research trend [J].Applied Soft Computing,2020,96(5):106582.
[6] PUNITHAVATHI R,RAMALINGAM A,KURANGI C,et al.Secure content based image retrieval system using deep learning with multi share creation scheme in cloud environment [J].Multimedia Tools and Applications,2021,80:26889-26910.
[7] RAHULAMATHAVAN Y,PHAN R C W,CHAMBERS J A,et al.Facial expression recognition in the encrypted domain based on local fisher discriminant analysis [J].IEEE Transactions on Affective Computing,2013,4:83-92.
[8] ALOTAIBI S,ALHARBI N,KURDI H.Face recognition under varying illumination based on homomorphic filter and local binary patterns [C]//2017 Intelligent Systems Conference.London:IEEE,2017:585-591.
[9] KUMAR S,SINGH S K,SINGH A K,et al.Privacy preserving security using biometrics in cloud computing [J].Multimedia Tools and Applications,2018,77(12):1-23.
[10] YANG T,MA J,MIAO Y,et al.PLCOM:Privacy-preserving outsourcing computation of Legendre circularly orthogonal moment over encrypted image data [J].Information Sciences,2019,505:198-214.
[11] WANG X,XUE H,LIU X,et al.A privacy-preserving edge computation-based face verification system for user authentication [J].IEEE Access,2019,7:14186-14197.
[12] ARNIA F,OKTIANA M,SADDAMI K,et al.Homomorphic filtering and phase-based matching for cross-spectral cross-distance face recognition [J].Sensors,2021,21(13):4575-4585.
[13] LFW.Labeled Faces in the Wild [DB/OL].(2018-01-09)[2021-06-15].http://vis-www.cs.umass.edu/lfw/.
[14] LIU J,WANG A,CHEN B,et al.Outsourced secure face recognition based on CKKS homomorphic encryption in cloud computing [J].International Journal of Mobile Computing and Multimedia Communications,2021,12(3):27-43.

[1]	田春婷, 赵宁, 秦建伟, 孟晓凤. 基于机器学习的红外光谱数据鉴别中药材性能方法[J]. 兰州理工大学学报, 2023, 49(3): 55-59.
[2]	王燕, 赵妮妮, 范林. 基于图神经网络特征交叉的协同过滤算法[J]. 兰州理工大学学报, 2023, 49(1): 94-102.
[3]	赵宏, 郑厚泽, 郭岚. 基于词-标签概率的多标签文本分类研究[J]. 兰州理工大学学报, 2023, 49(1): 103-109.
[4]	赵荣珍, 赵楠. 结合扰动集成RBF的故障识别方法[J]. 兰州理工大学学报, 2022, 48(6): 40-45.
[5]	郭晓斌, 袁冬芳, 曹富军. 基于深度神经网络的复杂区域偏微分方程求解[J]. 兰州理工大学学报, 2022, 48(6): 149-157.
[6]	张玺君, 王晨辉. 基于SARIMA-GA-Elman组合模型的短时交通流预测方法[J]. 兰州理工大学学报, 2022, 48(5): 107-113.
[7]	郭润兰, 史方青, 范雅琼, 何智. 基于卷积神经网络的壁面清洗机器人障碍物检测识别算法[J]. 兰州理工大学学报, 2022, 48(4): 83-89.
[8]	曹洁, 张敏, 张红, 陈作汉, 侯亮. 基于IFA优化RBF神经网络的短时交通流预测模型[J]. 兰州理工大学学报, 2022, 48(4): 99-104.
[9]	朱奇先, 梁浩鹏, 赵小强, 宋昭様. 基于残差神经网络的滚动轴承故障诊断方法[J]. 兰州理工大学学报, 2022, 48(3): 86-93.
[10]	赵荣珍, 马森财, 吴耀春. 云模型和集成极限学习机相结合的滚动轴承故障诊断方法[J]. 兰州理工大学学报, 2021, 47(4): 33-39.
[11]	刘金霞. 基于深度学习的无线电信号分类[J]. 兰州理工大学学报, 2021, 47(4): 106-110.
[12]	项长生, 原子, 周宇. 基于广义局部曲率模态信息熵和BP神经网络的结构损伤识别方法[J]. 兰州理工大学学报, 2021, 47(1): 129-135.
[13]	蒲浩, 黄建文, 秦进, 王正伟, 王杏. 具有变时滞的随机忆阻神经网络在固定时间内的控制同步[J]. 兰州理工大学学报, 2020, 46(5): 158-165.
[14]	张云, 李岚. 基于级联卷积神经网络的人脸特征点识别算法实现[J]. 兰州理工大学学报, 2020, 46(3): 105-109.
[15]	马栋林, 王孝通, 张澍寰, 郭娅婷. 基于用户行为的教学视频内容质量评价方法[J]. 兰州理工大学学报, 2020, 46(3): 110-115.

一种基于CKKS同态加密与神经网络的安全人脸识别方案

A secure face recognition scheme based on CKKS homomorphic encryption and neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价