基于隐私保护的反向传播神经网络学习算法

doi:10.11896/jsjkx.211100155

摘要/Abstract

摘要： 反向传播神经网络学习算法已经被广泛地应用在医疗诊断、生物信息学、入侵检测、国土安全等领域。这些应用领域的共同点是,都需要从大量的复杂的数据中抽取模式和预测趋势。在以上这些应用领域中,如何保护敏感数据和个人隐私信息是一个重要的问题。目前已有的反向传播神经网络学习算法,绝大多数都没有考虑在学习过程中如何保护数据的隐私信息。文中为反向传播神经网络提出基于隐私保护的算法,适用于数据被水平分割的情况。在建造神经网络的过程中,需要为训练样本集计算网络权向量。为了保证神经网络学习模型的隐私信息不被泄露,本文提出将权向量分配给所有参与方,使得每个参与方都具有权向量的一部分私有值。在对各层的神经元进行计算时,使用安全多方计算协议,从而保证神经网络权向量的中间值和最终值都是安全的。最后,被建造好的学习模型被所有参与方安全地共享,并且每个参与方可以使用该模型为各自的目标数据预测出相应的输出结果。实验结果表明,所提算法在执行时间和准确度误差上比传统非隐私保护算法更具优越性。

关键词: 安全多方计算, 神经网络, 隐私保护, 隐私泄露

Abstract: Back-propagation neural network learning algorithms based on privacy preserving are widely used in medical diagnosis,bioinformatics,intrusion detection,homeland security and other fields.The common of these applications is that all of them need to extract patterns and predict trends from a large number of complex data.In these applications,how to protect the privacy of sensitive data and personal information from disclosure is an important issue.At present,the vast majority of existing back-propagation neural network learning algorithms don't consider how to protect the data privacy in the process of learning.This paper proposes a back propagation neural network algorithm based on privacy-preserving,which is suitable for horizontally partitioned data.In the construction process of neural networks,it is need to compute network weight vector for the training sample set.To ensure the private information of neural network learning model can not be leaked,the weight vector will be assigned to all participants,so that each participant owns a part of private values of weight vector.In the calculation of neurons,we use secure multiparty computation,thus ensuring the middle and final values of the neural network weight vector are secure and will not be leaked.Finally,the constructed learning model will be securely shared by all participants,and each participant can use the model to predict the corresponding output for their respective target data.Experimental results show that the proposed algorithm has advantages over the traditional non-privacy protection algorithm in execution time and accuracy error.

Key words: Neural network, Privacy leakage, Privacy preserving, Secure multiparty computation

中图分类号:

TP183

王健. 基于隐私保护的反向传播神经网络学习算法[J]. 计算机科学, 2022, 49(6A): 575-580. https://doi.org/10.11896/jsjkx.211100155

WANG Jian. Back-propagation Neural Network Learning Algorithm Based on Privacy Preserving[J]. Computer Science, 2022, 49(6A): 575-580. https://doi.org/10.11896/jsjkx.211100155

参考文献

[1] WANG J,WANG L.A new anonymity-based protocol preserving privacy based cloud environment[J].Computer Modelling and New Technologies,2014,18(9):139-144.
[2] WILAMOWSKI B M.Neural network architectures and learning algorithms[J].Industrial Electronics Magazine,2009,3(4):56-63.
[3] FRYE R C,RIETMAN E A,WONG C C.Back-propagationlearning and nonidealities in analog neural network hardware[J].IEEE Trans on Neural Networks,1991,2(1):110-117.
[4] BARNI M,ORLANDI C,PIVA A.A privacy-preserving protocol for neural-network-based computation[C]//Proceedings of ACM MM&Sec'06.Geneva,Switzerland:ACM,2006:146-151.
[5] WAN L,NG W K,HAN S,et al.Privacy-preservation for gradient descent methods[C]//Proceedings of ACM SIGKDD' 07.New York:ACM,2007:775-783.
[6] SECRETAN J,GEORGIOPOULOS M,CASTRO J.A privacy preserving probabilistic neural network for horizontally partitioned databases[C]//Proceedings of IEEE IJCNN'07.Orlando,FL:IEEE,2007:1554-1559.
[7] CRAVEN M P,CURTIS K M,HAYES-GILL B R.Frequency division multiplexing in analogue neural network[J].Electro-nics Letters,1991,27(11):918-920.
[8] HUANG L,FENG D G,LIAN Y F,et al.Artificial-neural-network-based DDoS defense effectiveness evaluation[J].Journal of Computer Research and Development,2013,50(10):2100-2108.
[9] KODA M.Neural network learning based on stochastic sensitivity analysis[J].IEEE Trans on Cybernetics,1997,27(1):132-135.
[10] LI D L,LU D T,KONG X Y,et al.Implicit surfaces based on BP neural networks[J].Journal of Computer Research and Development,2007,44(3):467-472.
[11] ABHISHEK K,KUMAR A,RANJAN R,et al.A rainfall prediction model using artificial neural network[C]//Proceedings of IEEE ICSGRC'12.Shah Alam,Selangor:IEEE,2012:82-87.
[12] PASCAL P.Public-key cryptosystems based on composite degree residuosity classes[J].Lecture Notes in Computer Scien-ce,1999,1592(1):223-238.
[13] DHAKAR R S,GUPTA A K,SHARMA P.Modified RSA encryption algorithm[C]//Proceedings of IEEE ACCT'12.Rohtak,Haryana:IEEE,2012:426-429.
[14] ORLANDI C,PIVA A,BARNI M.Oblivious neural networkcomputing via homomorphic encryption[J].Journal of Information Security,2007,20(7):105-110.
[15] SAMET S,MIRI A.Privacy preserving ID3 using gini index over horizontally partitioned data[C]//Proceedings of IEEE AICCSA'08.Doha:IEEE,2008:645-651.
[16] CANETTI R.Security and composition of multiparty crypto-graphic protocols[J].Journal of Cryptology,2000,13(l):143-202.
[17] RANE S,SUN W,VETRO A.Secure function evaluation based on secret sharing and homomorphic encryption[C]//Procee-dings of IEEE CCAC'09.Monticello,IL:IEEE,2009:827-834.
[18] LINDA O,VOLLMER T,MANIC M.Neural network based intrusion detection system for critical infrastructures[C]//Proceedings of IEEE IJCNN'09.Atlanta,GA:IEEE,2009:1827-1834.
[19] RAFIQ M A,ROY N K,GHOSH B C.Three algorithms for learning artificial neural network:A comparison for induction motor flux estimation[C]//Proceedings of IEEE ICCIT '09.Dhaka:IEEE,2009:355-360.
[20] ADHIKARI S P,HYONGSUK K,BUDHATHOKI R K.A circuit-based learning architecture for multilayer neural networks with memristor bridge synapses[J].IEEE Transaction on Circuits and Systems,2015,62(1):215-223.
[21] SHEIKH S.Arabic-urdu script recognition through mouse:An implementation using artificial neural network[C]//Proceedings of IEEE ITNG'10.Las Vegas,NV:IEEE,2010:307-310.
[22] STEPHEN I,GALLANT.Neural network learning and expert systems [M].Massachusetts:MIT Press,1993.
[23] ZHAN J,MATWIN S.A crypto-based approach to privacy-preserving collaborative data mining[C]//Proceedings of IEEE ICDM'06.Hong Kong:IEEE,2006:546-550.

相关文章 15

[1]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[3]	鲁晨阳, 邓苏, 马武彬, 吴亚辉, 周浩浩. 基于分层抽样优化的面向异构客户端的联邦学习 Federated Learning Based on Stratified Sampling Optimization for Heterogeneous Clients 计算机科学, 2022, 49(9): 183-193. https://doi.org/10.11896/jsjkx.220500263
[4]	宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053
[5]	汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[6]	吕由, 吴文渊. 隐私保护线性回归方案与应用 Privacy-preserving Linear Regression Scheme and Its Application 计算机科学, 2022, 49(9): 318-325. https://doi.org/10.11896/jsjkx.220300190
[7]	窦家维. 保护隐私的汉明距离与编辑距离计算及应用 Privacy-preserving Hamming and Edit Distance Computation and Applications 计算机科学, 2022, 49(9): 355-360. https://doi.org/10.11896/jsjkx.220100241
[8]	王润安, 邹兆年. 基于物理操作级模型的查询执行时间预测方法 Query Performance Prediction Based on Physical Operation-level Models 计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074
[9]	陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[10]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[11]	檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[12]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[13]	李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[14]	郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[15]	齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed