秦宝东,李媛媛,余沛航

• 1:西安邮电大学网络空间安全学院

摘要(Abstract)：

针对基于线性函数的决策树隐私保护查询协议使用单比特同态加密比较算法，导致客户端的计算和通信开销较大问题，提出一种云计算辅助的高效决策树隐私保护查询协议。利用改进的双重ElGamal同态加密算法，将客户端与决策服务器之间执行的整数比较协议和决策节点选择协议转移至决策服务器与云计算辅助服务器之间，减少客户端的计算开销及其与服务器之间的通信开销，同时保护客户端的特征值信息和决策服务器的决策树模型信息的隐私。在乳腺癌数据集上的实验结果表明，该协议的客户端计算时间比基于线性函数的决策树隐私保护查询协议减少约41%,并且客户端与两个服务器之间的通信量减少约53.5%。

关键词(KeyWords)： 机器学习;决策树;隐私保护;同态加密;云计算

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(61872292);; 青海省基础研究计划项目(2020-ZJ-701)

作者(Author): 秦宝东,李媛媛,余沛航

DOI: 10.13682/j.issn.2095-6533.2022.01.001

参考文献(References)：

• [1] FLACH P.Machine learning-the art and science of algorithms that make sense of data[M].New York:Cambridge University Press,2012.
• [2] 潘晓英，王佳，刘妮，等.机器学习在医疗大数据中的应用[J].西安邮电大学学报，2020,25(1):21-33.PAN X J,WANG J,LIU N,et al.Application of machine learning in large medical data[J].Journal of Xi'an University of Posts and Telecommunications,2020,25(1):21-33.(in Chinese)
• [3] 纪守领，杜天宇，李进锋，等.机器学习模型安全与隐私研究综述[J].软件学报，2021,32(1):41-67.JI S L,DU T Y,LI J F,et al.Security and privacy of machine learning models:A survey[J].Journal of Software,2021,32(1):41-67.(in Chinese)
• [4] 赵镇东，常晓林，王逸翔.机器学习中的隐私保护综述[J].信息安全学报，2019,4(5):1-13.ZHAO Z D,CHANG X L,WANG Y X.A survey of privacy preserving in machine learning[J].Journal of Cyber Security,2019,4(5):1-13.(in Chinese)
• [5] 郑东，赵庆兰，张应辉.密码学综述[J].西安邮电大学学报，2013,18(6):1-10.ZHENG D,ZHAO Q L,ZHANG Y H.A brief overview on cryptography[J].Journal of Xi'an University of Posts and Telecommunicat,2013,18(6):1-10.(in Chinese)
• [6] ABADI M,CHU A,GOODFELLOW I J,et al.Deep learning with differential privacy[C]//Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security.Austria:ACM,2016:308-318.
• [7] GRAEPEL T,LAUTER K E,NAEHRIG M.ML confidential:Machine learning on encrypted data[C]//Proceedings of the Information Security and Cryptology-ICISC 2012 15th International Conference.Korea:Springer,2012:1-21.
• [8] 贾春福，王雅飞，陈阳，等.机器学习算法在同态加密数据集上的应用[J].清华大学学报(自然科学版),2020,60(6):456-463.JIA C F,WANG Y F,CHEN Y,et al.Machine learning algorithm for a homomorphic encrypted data set[J].Journal of Tsinghua University(Science and Technology),2020,60(6):456-463.(in Chinese)
• [9] TRAN A T,LUONG T D,KARNJANA J,et al.An efficient approach for privacy preserving decentralized deep learning models based on secure multi-party computation[J].Neurocomputing,2021,422:245-262.
• [10] BOST R,POPA R A,TU S,et al.Machine learning classification over encrypted data[C]//Proceedings of the Network and Distributed System Security Symposium.USA:The Internet Society,2015:1-14.
• [11] GILAD-BACHRACH R,DOWLIN N,LAINE K,et al.CryptoNets:Applying neural networks to encrypted data with high throughput and accuracy[C]//Proceedings of the 33nd International Conference on Machine Learning.USA:JMLR.org,2016:201-210.
• [12] WU D J,FENG T,NAEHRIG M,et al.Privately evaluating decision trees and random forests[J].Proceedings on Privacy Enhancing Technologies,2016(4):335-355.
• [13] TAI R K H,MA J P K,ZHAO Y J,et al.Privacy-preserving decision trees evaluation via linear functions[C]//Proceedings of the 22nd European Symposium on Research in Computer Security.Norway:Springer,2017:494-512.
• [14] ZHENG Y F,DUAN H Y,WANG C.Towards secure and efficient outsourcing of machine learning classification[C]//Proceedings of the 24th European Symposium on Research in Computer Security.Luxembourg:Springer,2019:22-40.
• [15] LIU L,CHEN R M,LIU X M,et al.Towards practical privacy-preserving decision tree training and evaluation in the cloud[J].IEEE Transactions on Information Forensics and Security,2020,15:2914-2929.
• [16] ELGAMAL T.A public key cryptosystem and a signature scheme based on discrete logarithms[J].IEEE Transactions on Information Theory,1985,31(4):469-472.
• [17] DAMG?RD I,GEISLER M,KR?IGAARD M.Homomorphic encryption and secure comparison[J].International Journal of Applied Cryptography,2008,1(1):22-31.