高效的隐私保护在线人脸认证方案

doi:10.11959/j.issn.1000-436x.2020087

通信学报 ›› 2020, Vol. 41 ›› Issue (5): 205-214.doi: 10.11959/j.issn.1000-436x.2020087

• 学术通信 • 上一篇

高效的隐私保护在线人脸认证方案

李明¹,杨晓鹏²(),朱辉²,王枫为²,李祁²

¹ 国家知识产权局专利局，北京 100088
² 西安电子科技大学综合业务网理论及关键技术国家重点实验室，陕西西安 710071

修回日期:2020-03-31 出版日期:2020-05-25 发布日期:2020-05-30
作者简介:李明（1977- ），男，陕西西安人，博士，国家知识产权局专利局研究员，主要研究方向为数据安全与应用安全|杨晓鹏（1991- ），男，河南林州人，西安电子科技大学博士生，主要研究方向为生物特征隐私保护、密码学及其应用|朱辉（1981- ），男，河南周口人，博士，西安电子科技大学教授、博士生导师，主要研究方向为数据安全与隐私保护、安全方案及协议设计、网络及应用安全等|王枫为（1993- ），男，河南周口人，西安电子科技大学博士生，主要研究方向为大数据安全与隐私保护与应用密码学|李祁（1994- ），男，江苏苏州人，西安电子科技大学硕士生，主要研究方向为大数据安全与隐私保护、应用密码学
基金资助:
国家重点研发计划基金资助项目(2017YFB0802200);国家自然科学基金资助项目(61972304);国家自然科学基金资助项目(61932015);陕西省重点研发计划基金资助项目(2019ZDLGY12-02);陕西省创新团队基金资助项目(2018TD-007)

Efficient and privacy-preserving online face authentication scheme

Ming LI¹,Xiaopeng YANG²(),Hui ZHU²,Fengwei WANG²,Qi LI²

¹ Patent Office,China National Intellectual Property Administration,Beijing 100088,China
² State Key Laboratory of Integrated Services Networks,Xidian University,Xi’an 710071,China

Revised:2020-03-31 Online:2020-05-25 Published:2020-05-30
Supported by:
The National Key Research and Development Program of China(2017YFB0802200);The National Natural Science Foundation of China(61972304);The National Natural Science Foundation of China(61932015);The Shannxi Provincial Key Research and Development Program(2019ZDLGY12-02);The Innovation Team Project of Shannxi Province(2018TD-007)

摘要/Abstract

摘要：

在传统人脸认证系统中，用户特征模板和认证请求通常基于明文进行匹配，存在敏感数据泄露的风险。针对此问题，提出了一种基于矩阵加密的隐私保护的在线人脸认证方案。该方案中，用户的人脸特征模板注册和后续身份认证请求均通过矩阵加密后分别发送给在线认证服务器，并由在线认证服务器完成密文下两者间的相似度计算，能够在不影响认证精确度的同时，有效保护在线人脸认证过程中用户的敏感数据。安全性分析表明，通过选取不同安全参数，所提方案能够实现多安全等级，满足差异化场景中的隐私保护需求。性能分析显示，所提方案具有较低的计算开销与通信开销。仿真测试基于真实人脸数据库，其结果验证了所提方案的高效性，能够在真实环境中进行有效应用。

关键词: 在线人脸认证, 隐私保护, 矩阵加密, 生物特征模板

Abstract:

In traditional face authentication system,the trait template and authentication request were generally matched over plaintext,which may lead to the leakage of users’ sensitive data.In order to address the above-mentioned problem,based on matrix encryption,an efficient and privacy-preserving online face authentication scheme was proposed.Specifically,the users’ face trait template for register and the authentication request were encrypted before being sent to the online authentication server,and the similarity computation between the encrypted face trait template and authentication request was computed by the online authentication server over ciphertexts,which guaranteed the security of users’ sensitive data without affecting the accuracy of face authentication.Security analysis shows that the proposed scheme can achieve multiple security levels according to different security parameters.Moreover,performance evaluation shows that the proposed scheme has low computation cost and communication overhead.Experiments results demonstrate the high efficiency of the proposed scheme,which can be implemented in the real environment effectively.

Key words: online face authentication, privacy-preserving, matrix encryption, biometric template

中图分类号:

TP302

李明,杨晓鹏,朱辉,王枫为,李祁. 高效的隐私保护在线人脸认证方案[J]. 通信学报, 2020, 41(5): 205-214.

Ming LI,Xiaopeng YANG,Hui ZHU,Fengwei WANG,Qi LI. Efficient and privacy-preserving online face authentication scheme[J]. Journal on Communications, 2020, 41(5): 205-214.

图/表 9

图1

表1

方案中相关符号及其含义"

符号	含义
h	用户图像长的像素数
w	用户图像宽的像素数
N	用户图像的像素数
k	选择的特征向量数
$M_{i}$	可逆随机矩阵
$M_{i}^{- 1}$	可逆随机矩阵的逆矩阵
Z	非负整数
$H$	随机向量
diag()	将向量转换为对角矩阵
A	一个随机矩阵
${C_{D_{1}}, C_{D_{2}}, \cdot \cdot \cdot, C_{D_{P}}}$	加密后的用户生物特征模板
{L₁,L₂,???,L_P}	用户生物特征模板的模长
$C_{A}$	加密后的身份认证凭据
L_new	身份认证凭据的模长
UID	用户的身份标识
r ₁,r₂,…,r _Z	用户选择的一组随机数
score_i	用户人脸特征模板和身份认证凭据模板之间的相似度
θ	系统判别门限值

表1

图2

表2

表3

图3

图4

图5

图6

参考文献 28

[1]	SPREEUWERS L J , HENDRIKSE A J , GERRITSEN K J . Evaluation of automatic face recognition for automatic border control on actual data recorded of travellers at schiphol airport[C]// International Conference of Biometrics Special Interest Group. Piscataway:IEEE Press, 2012: 1-6.
[2]	SAMANTHA S . Credit card with a fingerprint sensor revealed by mastercard[EB].(2017-04-20)[2020-03-08].
[3]	RICHARD W . Face recognition tested to monitor terrorist suspects[EB].(2017-07-20)[2020-03-08].
[4]	WU H . Alleged breach of India's biometric database could put 1.2bn users at risk[EB].(2018-01-11)[2020-03-08].
[5]	Avast Security News Team . Biometric security platform leaves 28M records unsecured[EB].(2019-08-16[2020-03-08].
[6]	LI Q , ZHU H , ZHANG Z ,et al. Spoofing attacks on speaker verification systems based generated voice using genetic algorithm[C]// 2019 IEEE International Conference on Communications. Piscataway:IEEE Press, 2019: 1-6.
[7]	李凤华, 李晖, 贾焰 ,等. 隐私计算研究范畴及发展趋势[J]. 通信学报, 2016,37(4): 1-11.
	LI F H , LI H , JIA Y ,et al. Privacy computing:concept,connotation and its research trend[J]. Journal on Communications, 2016,37(4): 1-11.
[8]	BENSON B . Fingerprint not recognized:why the united states needs to protect biometric privacy[J]. North Carolina Journal of Law ＆Technology, 2018,19(4): 161-192.
[9]	LI F H , LI H , NIU B ,et al. Privacy computing:concept,computing framework,and future development trends[J]. Engineering, 2019,5(9): 1179-1192.
[10]	朱辉, 武衡, 赵海强 ,等. 适用于双层卫星网络的星间组网认证方案[J]. 通信学报, 2019,40(3): 1-9.
	ZHU H , WU H , ZHAO H Q ,et al. Efficient authentication scheme for double-layer satellite network[J]. Journal on Communications, 2019,40(3): 1-9.
[11]	ERKIN Z , FRANZ M , GUAJARDO J ,et al. Privacy-preserving face recognition[C]// International Symposium on Privacy Enhancing Technologies Symposium. Berlin:Springer, 2009: 235-253.
[12]	DAMGARD I. , GEISLER M , KRIGAARD M ,et al. Efficient and secure comparison for on-line auctions[C]// Australasian Conference on Information Security and Privacy. Berlin:Springer, 2007: 416-430.
[13]	SADEGHI A , SCHNEIDER T , WEHRENBERG I . Efficient privacy-preserving face recognition[C]// International Conference on Information Security and Cryptology. Berlin:Springer, 2009: 229-244.
[14]	XIANG C , TANG C , CAI Y ,et al. Privacy-preserving face recognition with outsourced computation[J]. Soft Computing, 2016,20(9): 3735-3744.
[15]	ZHU H , WEI Q , YANG X P ,et al. Efficient and privacy-preserving online fingerprint authentication scheme over outsourced data[J]. IEEE Transactions on Cloud Computing, 2018:1.
[16]	YUAN J , YU S . Efficient privacy-preserving biometric identification in cloud computing[C]// 2013 Proceedings IEEE International Conference on Computer Communications. Piscataway:IEEE Press, 2013: 2652-2660.
[17]	WANG Q , HU S , REN K ,et al. CloudBI:practical privacy-preserving outsourcing of biometric identification in the cloud[C]// European Symposium on Research in Computer Security. Berlin:Springer, 2015: 186-205.
[18]	ZHU L , ZHANG C , XU C ,et al. An efficient and privacy-preserving biometric identification scheme in cloud computing[J]. IEEE Access, 2018(6): 19025-19033.
[19]	RAHULAMATHAVAN Y , RAJARAJAN M . Hide-and-seek:face recognition in private[C]// 2015 IEEE International Conference on Communications. Piscataway:IEEE Press, 2015: 7102-7107.
[20]	GUNASINGHE H , BERTINO E . PrivBioMTAuth:privacy preserving biometrics-based and user centric protocol for user authentication from mobile phones[J]. IEEE Transactions on Information Forensics ＆ Security, 2018,13(4): 1042-1057.
[21]	SARIER N D , . Privacy preserving biometric identification on the bitcoin blockchain[C]// 2018 International Symposium on Cyberspace Safety and Security. Berlin:Springer, 2018: 254-269.
[22]	TURK M A , PENTLAND A P . Face recognition using eigenfaces[C]// Proceedings of 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 1991: 586-591.
[23]	GUPTA S , SAHOO O P , GOEL A ,et al. A new optimized approach to face recognition using eigenfaces[J]. Global Journal of Computer Science and Technology, 2010(10): 15-17.
[24]	SHAN S , CAO B , GAO W ,et al. Extended fisherface for face recognition from a single example image per person[C]// 2002 IEEE International Symposium on Circuits and Systems.Proceedings. Piscataway:IEEE Press, 2002,(2): 81-84.
[25]	LIU K , GIANNELLA C , KARGUPTA H . An attacker’s view of distance preserving maps for privacy preserving data mining[C]// European Conference on Principles of Data Mining and Knowledge Discovery. Berlin:Springer, 2006: 297-308.
[26]	CAO N , YANG Z , WANG C ,et al. Privacy-preserving query over encrypted graph-structured data in cloud computing[C]// 2011 31st International Conference on Distributed Computing Systems. Piscataway:IEEE Press, 2011: 393-402.
[27]	WONG W K , CHEUNG D W , KAO B ,et al. Secure KNN computation on encrypted databases[C]// Proceedings of the 2009 ACM SIGMOD International Conference on Management of data. New York:ACM Press, 2009: 139-152.
[28]	AT＆T Laboratories Cambridge. The ORL database of faces[DB]. AT＆T Labs Research,[2020-03-08].

方案	保护用户模板	保护用户认证凭据安全	满足攻击模型I下安全	在攻击模型II中安全	在攻击模型III中安全
本文方案	是	是	当Z=0时满足	当Z=1时满足	当Z=2时满足
文献[12]方案	是	是	是	是	是

方案	注册阶段/bit	认证阶段/bit
原始方案	64(Pk+1)	64k
本文方案	64(P(k+2Z) ²+P)	256Z+128k+64
文献[12]方案	2 048N+7 168	2048k+2 048P+9126

高效的隐私保护在线人脸认证方案

Efficient and privacy-preserving online face authentication scheme

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 28

相关文章 15

Metrics

推荐阅读 0

[1]	马鑫迪, 李清华, 姜奇, 马卓, 高胜, 田有亮, 马建峰. 面向Non-IID数据的拜占庭鲁棒联邦学习[J]. 通信学报, 2023, 44(6): 138-153.
[2]	冯涛, 陈李秋, 方君丽, 石建明. 基于本地化差分隐私和属性基可搜索加密的区块链数据共享方案[J]. 通信学报, 2023, 44(5): 224-233.
[3]	夏莹杰, 朱思雨, 刘雪娇. 区块链架构下具有条件隐私的车辆编队跨信任域高效群组认证研究[J]. 通信学报, 2023, 44(4): 111-123.
[4]	胡柏吉, 张晓娟, 李元诚, 赖荣鑫. 支持多功能的V2G网络隐私保护数据聚合方案[J]. 通信学报, 2023, 44(4): 187-200.
[5]	徐明, 张保俊, 伍益明, 应晨铎, 郑宁. 面向网络攻击和隐私保护的多智能体系统分布式共识算法[J]. 通信学报, 2023, 44(3): 117-127.
[6]	余晟兴, 陈钟. 基于同态加密的高效安全联邦学习聚合框架[J]. 通信学报, 2023, 44(1): 14-28.
[7]	张学旺, 黎志鸿, 林金朝. 基于公平盲签名和分级加密的联盟链隐私保护方案[J]. 通信学报, 2022, 43(8): 131-141.
[8]	王继锋, 王国峰. 边缘计算模式下密文搜索与共享技术研究[J]. 通信学报, 2022, 43(4): 227-238.
[9]	封化民, 史瑞, 袁峰, 李艳俊, 杨旸. 高效的强隐私保护和可转让的属性票据方案[J]. 通信学报, 2022, 43(3): 63-75.
[10]	于海宁, 张宏莉, 余翔湛, 曲家兴, 葛蒙蒙. 隐私保护的轨迹相似度计算方法[J]. 通信学报, 2022, 43(11): 1-13.
[11]	彭滔, 钟文韬, 王国军, 罗恩韬, 熊金波, 刘忆宁, Hao Wang. 移动社交网络中面向隐私保护的精确好友匹配[J]. 通信学报, 2022, 43(11): 90-103.
[12]	史瑞, 封化民, 谢惠琴, 史国振, 刘飚, 杨旸. 基于带智能卡的移动终端实现的隐私保护的属性票据方案[J]. 通信学报, 2022, 43(10): 26-41.
[13]	熊金波, 周永洁, 毕仁万, 万良, 田有亮. 边缘协同的轻量级隐私保护分类框架[J]. 通信学报, 2022, 43(1): 127-137.
[14]	晏燕, 丛一鸣, Adnan Mahmood, 盛权政. 基于深度学习的位置大数据统计发布与隐私保护方法[J]. 通信学报, 2022, 43(1): 203-216.
[15]	马立川, 彭佳怡, 裴庆祺, 朱浩瑾. 高效的决策树隐私分类服务协议[J]. 通信学报, 2021, 42(8): 80-89.