面向ASPE的抗合谋攻击图像检索隐私保护方案

doi:10.19665/j.issn1001-2400.20230406

摘要/Abstract

摘要：

现有的基于非对称内积标量保留加密算法(ASPE)实现了云计算下图像检索中的隐私保护,但由于检索时云服务提供商和检索用户不可信以及外部敌手的存在,无法抵抗恶意用户与云服务器的合谋攻击,可能导致包含敏感信息的图像数据泄露。针对多用户场景,提出了一种面向ASPE的抗合谋攻击图像检索隐私保护方案。首先,该方案通过代理重加密解决因向不可信用户传输私钥导致的图像密钥泄露问题;其次,在客户端添加对角矩阵加密解决云服务提供商和检索用户之间因合谋攻击导致的特征密钥泄露问题;最后,通过线性判别分析来解决局部敏感哈希构建索引时因降维导致的检索准确率下降问题。通过安全性分析证明,该方案是安全且有效的,不仅能够抵抗来自云服务提供商和不可信用户的合谋攻击、唯密文攻击、已知背景攻击和已知明文攻击,同时能够实现对检索过程中图像与私钥的保护。实验结果表明,所提方案在保护图像隐私及保证检索效率的前提下,密文域和明文域的检索精度仅相差约2%。

关键词: 图像检索, 隐私保护技术, 云计算, 合谋攻击, 局部敏感哈希

Abstract:

The existing algorithm based on Asymmetric Scalar-Product-Preserving Encryption (ASPE) realizes privacy protection in image retrieval under cloud computing.But due to untrustworthy cloud service providers and retrieval users during retrieval and the existence of an external adversary,it cannot resist the collusion attack of malicious users and cloud servers,which may lead to the leakage of image data containing sensitive information.Aiming at multi-user scenarios,an Anti-collusion attack image retrieval privacy protection scheme for ASPE is proposed.First,the scheme uses proxy re-encryption to solve the problem of image key leakage caused by transmitting private keys to untrusted users.Second,the feature key leakage problem between the cloud service provider and the retrieval user due to collusion attacks is solved by adding a diagonal matrix encryption at the client side.Finally,linear discriminant analysis is used to solve the problem of retrieval accuracy drop caused by dimensionality reduction when locality sensitive hashing is used to construct an index.The security analysis proves that the scheme is safe and effective and that it can not only resist collusion attacks from cloud service providers and untrusted users,ciphertext-only attacks,known background attacks and known plaintext attacks,but also realize protection of images and private keys during the process.Experimental results show that under the premise of protecting image privacy and ensuring retrieval efficiency,the retrieval accuracy of the proposed scheme in the ciphertext domain and that in the plaintext domain are only about 2% different.

Key words: image retrieval, privacy-preserving techniques, cloud computing, collusion attacks, locality sensitive hashing

中图分类号:

TP309

蔡英,张猛,李新,张宇,范艳芳. 面向ASPE的抗合谋攻击图像检索隐私保护方案[J]. 西安电子科技大学学报, 2023, 50(5): 156-165.

CAI Ying,ZHANG Meng,LI Xin,ZHANG Yu,FAN Yanfang. Anti-collusion attack image retrieval privacy protection scheme for ASPE[J]. Journal of Xidian University, 2023, 50(5): 156-165.

图/表 12

图1

图2

表1

表2

表3

表4

图3

图4

图5

图6

图7

图8

参考文献 19

[1]	杨海滨, 李瑞峰, 易铮阁, 等. 无双线性对的高效云存储数据审计方案[J]. 西安电子科技大学学报, 2022, 49(1):47-54.
	YANG Haibin, LI Ruifeng, YI Zhengge, et al. Efficient Cloud Storage Data Auditing Scheme without Bilinear Pairing[J]. Journal of Xidian University, 2022, 49(1):47-54.
[2]	ZHANG M, CAI Y, ZHANG Y, et al. A Survey on Content-Based Encrypted Image Retrieval in Cloud Computing[C]//2021 3rd International Conference on Big Data and Security.Heidelberg:Springer, 2022:312-325.
[3]	WENG W, YAKIMENK Y, LIN Y, et al. Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval[J]. IEEE Transactions on Information Forensics and Security, 2022, 17:3495-3510. doi: 10.1109/TIFS.2022.3203320
[4]	闫玺玺, 赵强, 汤永利, 等. 支持灵活访问控制的多关键字搜索加密方案[J]. 西安电子科技大学学报, 2022, 49(1):55-66.
	YAN Xixi, ZHAO Qiang, TANG Yongli, et al. Multi-Keyword Search Encryption Scheme Supporting Flexible Access Control[J]. Journal of Xidian University, 2022, 49(1):55-66.
[5]	LI Y, MA J, MIAO Y, et al. Traceable and Controllable Encrypted Cloud Image Search in Multi-User Settings[J]. IEEE Transactions on Cloud Computing, 2022, 10(4):2936-2948. doi: 10.1109/TCC.2020.3034232
[6]	LI Y, MA J, MIAO Y, et al. DVREI:Dynamic Verifiable Retrieval Over Encrypted Images[J]. IEEE Transactions on Computers, 2022, 71(8):1755-1769.
[7]	DONG X, ZHANG W, SHAH M, et al. Watermarking-Based Secure Plaintext Image Protocols for Storage,Show,Deletion and Retrieval in the Cloud[J]. IEEE Transactions on Services Computing, 2022, 15(3):1678-1692. doi: 10.1109/TSC.2020.3008957
[8]	SONG L, MIAO Y, WENG J, et al. Privacy-Preserving Threshold-Based Image Retrieval in Cloud-Assisted Internet of Things[J]. IEEE Internet of Things Journal, 2022, 9(15):13598-13611. doi: 10.1109/JIOT.2022.3142933
[9]	XIA Z, JIANG L, LIU D, et al. BOEW:A Content-Based Image Retrieval Scheme Using Bag-of-Encrypted-Words in Cloud Computing[J]. IEEE Transactions on Services Computing, 2022, 15(1):202-214. doi: 10.1109/TSC.2019.2927215
[10]	宋甫元, 秦拯, 张吉昕, 等. 基于访问控制安全高效的多用户外包图像检索方案[J]. 网络与信息安全学报, 2021, 7(5):29-39.
	SONG Fuyuan, QIN Zheng, ZHANG Jixin, et al. Efficient and Secure Multi-User Outsourced Image Retrieval Scheme with Access Control[J]. Chinese Journal of Network and Information Security, 2021, 7(5):29-39.
[11]	DING Y, TAN F, QIN Z, et al. DeepKeyGen:A Deep Learning-Based Stream Cipher Generator for Medical Image Encryption and Decryption[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(9):4915-4929. doi: 10.1109/TNNLS.2021.3062754
[12]	LI F, SHUGUROV I, BUSAM B, et al. WS-OPE:Weakly Supervised 6-D Object Pose Regression Using Relative Multi-Camera Pose Constraints[J]. IEEE Robotics and Automation Letters, 2022, 7(2):3703-3710. doi: 10.1109/LRA.2022.3146924
[13]	LI S, ZHAO S, MIN G, et al. Lightweight Privacy-Preserving Scheme Using HomomorphicEncryption in Industrial Internet of Things[J]. IEEE Internet of Things Journal, 2022, 9(16):14542-14550. doi: 10.1109/JIOT.2021.3066427
[14]	IIDA K, KIYA H. A Privacy-Preserving Image Retrieval Scheme with a Mixture of Plain and EtC Images[C]//2022 IEEE 4th Global Conference on Life Sciences and Technologies (LifeTech).Piscataway:IEEE, 2022:183-186.
[15]	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, 2009:139-152.
[16]	YUAN J, TIAN Y. Practical Privacy-Preserving Mapreduce Based k-Means Clustering over Large-Scale Dataset[J]. IEEE Transactions on Cloud Computing, 2017, 7(2):568-579. doi: 10.1109/TCC.6245519
[17]	SONG F, QIN Z, ZHANG J, et al. Efficient and Privacy-Preserving Outsourced Image Retrieval in Public Clouds[C]//GLOBECOM 2020-2020 IEEE Global Communications Conference.Piscataway:IEEE, 2020:1-6.
[18]	LI Y, MA J, MIAO Y, et al. Similarity Search for Encrypted Images in Secure Cloud Computing[J]. IEEE Transactions on Cloud Computing, 2022, 10(2):1142-1155. doi: 10.1109/TCC.2020.2989923
[19]	LI X, XUE Q, CHUAH M C. Casheirs:Cloud Assisted Scalable Hierarchical Encrypted Based Image Retrieval System[C]//IEEE INFOCOM 2017-IEEE Conference on Computer Communications. Piscataway:IEEE, 2017:1-9.

符号	描述
G/W/c_o_→_u	公钥集/私钥集/重加密密钥
P/C,n	明文/密文图像集
A/B/M₁/M₂	ASPE算法中的参数
n/h	图像数量/用户数量
R/R'	检索结果/重加密结果
F/d	特征集/特征维数
H/v	局部敏感哈希函数的参数
M_L/E_U	线性判别分析/欧氏距离

方案	索引构建	陷门生成	图像检索
CSM^[5]	2n(2d+2+h)²	2(2d+2+h)²	2m(2d+2+h)²
文献[10]	n(d+3+h)²	(d+3+h)²	m(d+3+h)²
文中方案	2n(2d)²	2(2d)²	2(m-s)(2d)²

方案	图像拥有者	查询用户	云服务器
CSM^[5]	n(4d+4+2h+\|λ\|)	4d+4+2h	K\|λ\|
文献[10]	n(d+3+h+\|λ\|)	d+3+h	K\|λ\|
文中方案	n(4d+\|λ\|)	4d	K\|λ\|

d	K=5	K=10	K=20	K=30	K=40
CNN-32	86.23	74.57	71.36	67.25	66.37
CNN-64	93.28	90.54	88.64	87.53	71.32
CNN-128	94.17	92.16	89.12	87.67	76.39
CNN-256	89.33	84.24	76.75	75.63	61.37
CNN-512	87.53	76.45	76.19	67.48	64.15