计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (9): 26-34.doi: 10.11896/jsjkx.230400033

• 数据安全 • 上一篇    下一篇

基于SecureCNN的高效加密图像内容检索系统

卢雨晗, 陈立全, 王宇, 胡致远   

  1. 东南大学网络空间安全学院 南京 210000
  • 收稿日期:2023-04-05 修回日期:2023-07-07 出版日期:2023-09-15 发布日期:2023-09-01
  • 通讯作者: 陈立全(Lqchen@seu.edu.cn)
  • 作者简介:(Lyh_230701@163.com)
  • 基金资助:
    国家重点研发计划(2020YFE0200600);国家自然科学基金(62002058)

Efficient Encrypted Image Content Retrieval System Based on SecureCNN

LU Yuhan, CHEN Liquan, WANG Yu, HU Zhiyuan   

  1. School of Cyberspace Security,Southeast University,Nanjing 210000,China
  • Received:2023-04-05 Revised:2023-07-07 Online:2023-09-15 Published:2023-09-01
  • About author:LU Yuhan,born in 1999,postgraduate.Her main research interests include image security retrieval and so on.
    CHEN Liquan,born in 1976,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.His main research interests include information security,cryptography and network security protocol,etc.
  • Supported by:
    National Key R & D Program of China(2020YFE0200600)and National Natural Science Foundation of China(62002058).

PDF (PC)

2512

摘要： 随着智能设备的快速发展,云上的基于内容的图像检索技术(CBIR)越来越受欢迎。但在半诚实的云服务器上进行图像检索存在泄露用户隐私的风险。为了防止个人隐私遭到泄露,用户外包图像给云之前会对其进行加密,但现有的明文域上CBIR方案对于加密图像数据的搜索是无效的。为了解决这些问题,文中提出了一个基于近似数同态的高效加密图像内容检索方案,在保护用户隐私的情况下,能够快速实现以图搜图,且无需用户的持续交互。首先使用近似数同态神经网络对图像集进行特征提取,可以保证网络模型的参数和图像集数据不会泄露给云服务器。其次,提出了一种新的神经网络分治方法,该方法可以减少同态加密乘法深度和提高模型运行效率;利用分级可导航小世界(HNSW)算法构造索引,实现高效图像检索。此外,使用同态加密保障图像数据传输过程的安全性,使用对称加密算法保证存储阶段的安全性。最后,通过实验对比和安全性分析证明了该方案的安全性和效率。实验结果表明,该方案是IND-CCA的,且在保证图像私密性的前提下,其同态加密的乘法次数最多为3次,在检索精度上远超过现有方案,在检索时间复杂度方面比现有方案高出至少100倍,实现了检索精度和效率的兼顾。

关键词: 近似同态, 基于内容的图像检索技术, 神经网络, 分级可导航小世界图算法, 高效检索

Abstract: With the rapid development of smart devices,content-based image retrieval technology(CBIR) on the cloud is becoming increasingly popular.However,image retrieval on a semi-honest cloud server carries the risk of compromising user privacy.To prevent personal privacy from being compromised,users encrypt their images before outsourcing them to the cloud,but existing CBIR schemes on plaintext domains are ineffective for searching encrypted image data.To solve these problems,an efficient encrypted image content retrieval scheme based on approximate number homomorphism is proposed in the paper,which can quickly achieve image search without continuous user interaction while protecting user privacy.Firstly,feature extraction of image sets using approximate number homomorphism neural network can ensure that the parameters of the network model and the image set data are not leaked to the cloud server.Secondly,a new neural network partitioning method is also proposed to reduce the homomorphic encryption multiplication depth and improve the model operation efficiency,and also construct the index using hierarchical navigable small world(HNSW) algorithm to achieve efficient image retrieval.In addition,homomorphic encryption is used to guarantee the security of image data transmission process and symmetric encryption algorithm is used to guarantee the security of storage stage.Finally,the security and efficiency of the scheme are proved by experimental comparison and security analysis.Experimental results show that the scheme is IND-CCA,and the number of multiplications of homomorphic encryption in this scheme is at most 3 times while guaranteeing the image privacy,which far exceeds the existing schemes in terms of retrieval accuracy and at least 100 times higher than the existing schemes in terms of retrieval time complexity,achieving a balance of retrieval accuracy and efficiency.

Key words: Approximately homomorphic, Content-based image retrieval, Neural Network, Hierarchical navigable small world algorithm, Efficient search

中图分类号: 

  • TP391.41
[1]LI X,YANG J,MA J.Recent developments of content-basedimage retrieval(CBIR)[J].Neurocomputing,2021,452:675-689.
[2]HE Y,CHEN L,NI Y,et al.Privacy protection scheme for edge computing based on function encryption[C]//2021 International Conference on Networking and Network Applications(NaNA).IEEE,2021:131-135.
[3]LIU W,WU D J.Research progress on privacy protection ofmedical information[J].Software,2020,41(5):74-79.
[4]2020 Data Breach Incident Report in the U.S.Healthcare Industry [EB/OL].www.mchz.com.cn.
[5]WANG H,XIA Z,FEI J,et al.An AES-based secure image retrieval scheme using random mapping and BOW in cloud computing[J].IEEE Access,2020,8:61138-61147.
[6]AGRAWAL R,KIERNAN J,SRIKANT R,et al.Order preserving encryption for numeric data[C]//Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data.2004:563-574.
[7]FURUKAWA J.Request-based comparable encryption[C]//European symposium on research in computer security.Berlin:Springer,2013:129-146.
[8]CHEN P,YE J,CHEN X.Efficient request-based comparable encryption scheme based on sliding window method[J].Soft Computing,2016,20:4589-4596.
[9]ZOU Q,WANG J,YE J,et al.Efficient and secure encryptedimage search in mobile cloud computing[J].Soft Computing,2017,21:2959-2969.
[10]QIN Z,YAN J,REN K,et al.Towards efficient privacy-preserving image feature extraction in cloud computing[C]//Procee-dings of the 22nd ACM International Conference on Multimedia.2014:497-506.
[11]FENG Q,LI P,LU Z,et al.DHAN:Encrypted JPEG image retrieval via DCT histograms-based attention networks[J].Applied Soft Computing,2023,133:109935.
[12]ZHANG C,LI J,WANG S,et al.An encrypted medical image retrieval algorithm based on DWT-DCT frequency domain[C]//2017 IEEE 15th International Conference on Software Enginee-ring Research,Management and Applications(SERA).IEEE,2017:135-141.
[13]GILAD-BACHRACH R,DOWLIN N,LAINE K,et al.Cryp-tonets:Applying neural networks to encrypted data with high throughput and accuracy[C]//International Conference on Machine Learning.PMLR,2016:201-210.
[14]CHOU E,BEAL J,LEVY D,et al.Faster cryptonets:Leveraging sparsity for real-world encrypted inference[J].arXiv:1811.09953,2018.
[15]JUVEKAR C,VAIKUNTANATHAN V,CHANDRAKASAN A.{GAZELLE}:A low latency framework for secure neural network inference[C]//27th {USENIX} Security Symposium({USENIX} Security 18).2018:1651-1669.
[16]PERETEANU G L,ALANSARY A,PASSERAT-PALMBACHJ.Split HE:Fast secure inference combining split lear-ning and homomorphic encryption[J].arXiv:2202.13351,2022.
[17]CHEON J H,KIM A,KIM M,et al.Homomorphic encryption for arithmetic of approximate numbers[C]//Advances in Cryptology-ASIACRYPT 2017:23rd International Conference on the Theory and Applications of Cryptology and Information Security.Springer International Publishing,2017:409-437.
[18]GALLEGO A J,RICO-JUAN J R,VALERO-MAS J J.Efficient k-nearest neighbor search based on clustering and adaptive k values[J].Pattern Recognition,2022,122:108356.
[19]LI W,ZHANG Y,SUN Y,et al.Approximate nearest neighbor search on high dimensional data—experiments,analyses,and improvement[J].IEEE Transactions on Knowledge and Data Engineering,2019,32(8):1475-1488.
[20]BELARBI M A,MAHMOUDI S,BELALEM G,et al.A NewComparative Study of Dimensionality Reduction Methods in Large-Scale Image Retrieval[J].Big Data and Cognitive Computing,2022,6(2):54.
[21]THAKUR N,REIMERS N,LIN J.Domain adaptation for me-mory-efficient dense retrieval[J].arXiv:2205.11498,2022.
[22]MALKOV Y A,YASHUNIN D A.Efficient and robust appro-ximate nearest neighbor search using hierarchical navigable small world graphs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,42(4):824-836.
[23]IOFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning.PMLR,2015:448-456.
[24]HESAMIFARD E,TAKABI H,GHASEMI M.Cryptodl:Deep neural networks over encrypted data[J].arXiv:1711.05189,2017.
[25]WANG Y,CHEN L,WU G,et al.Efficient and secure content-based image retrieval with deep neural networks in the mobile cloud computing[J].Computers & Security,2023,128:103163.
[26]CHENG K,FU J,SHEN Y,et al.Manto:A Practical and Secure Inference Service of Convolutional Neural Networks for IoT[J].IEEE Internet of Things Journal,doi:10.1109/JIOT.2023.3251982.
[27]SRINIVASAN W Z,AKSHAYARAM P,ADA P R.DELPHI:A cryptographic inference service for neural networks[C]//Proceedings of 29th USENIX Security.2019:2505-2522.
[28]XIA Z,XIONG N N,VASILAKOS A V,et al.EPCBIR:An efficient and privacy-preserving content-based image retrieval scheme in cloud computing[J].Information Sciences,2017,387:195-204.
[29]WANG Z,QIN J,XIANG X,et al.A privacy-preserving andtraitor tracking content-based image retrieval scheme in cloud computing[J].Multimedia Systems,2021,27:403-415.
[30]LEE J W,KANG H,LEE Y,et al.Privacy-preserving machine learning with fully homomorphic encryption for deep neural network[J].arXiv:2106.07229,2021.
[31]RATHEE D,RATHEE M,KUMAR N,et al.CrypTFlow2:Practical 2-party secure inference[C]//Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security.2020:325-342.
[32]HUANG Z,LU W,HONG C,et al.Cheetah:Lean and Fast Secure {Two-Party} Deep Neural Network Inference[C]//31st USENIX Security Symposium(USENIX Security 22).2022:809-826.
[33]HASSAN A,LIU F,WANG F,et al.Secure content basedimage retrieval for mobile users with deep neural networks in the cloud[J].Journal of Systems Architecture,2021,116:102043.
[34]WANG Z,QIN J,XIANG X,et al.A privacy-preserving andtraitor tracking content-based image retrieval scheme in cloud computing[J].Multimedia Systems,2021,27:403-415.
[35]SHEN M,CHENG G,ZHU L,et al.Content-based multi-source encrypted image retrieval in clouds with privacy preservation[J].Future Generation Computer Systems,2020,109:621-632.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发