计算机应用研究2024，Vol.41Issue(6)：1851-1861,11.DOI:10.19734/j.issn.1001-3695.2023.09.0403
梯度隐藏的安全聚类与隐私保护联邦学习
Gradient-hiding secure clustering and privacy-preserving federated learning
摘要
Abstract
Federated learning is a kind of advanced distributed machine learning algorithm,which realizes multi-party cooperative training while ensuring the user's control over the data.However,the existing federated learning algorithms have many problems in dealing with Non-IID data,gradient information leakage and dynamic user offline.To solve these problems,this paper proposed a gradient hidden safe clustering and privacy-protecting federated learning based on quaternion,zero sha-ring and secret sharing techniques.Firstly,it used quaternion rotation technology to hide the first-round model gradient and achieve secure clustering stratification without altering the gradient feature distribution,so as to solve the performance degrada-tion issue caused by Non-IID data.Secondly,this paper designed a chain zero sharing algorithm,using single strategy to pro-tect the user model gradient mask.Then,it used the threshold secret sharing to improve the robustness against offline users.Multi-dimensional comparison with other existing algorithms shows that the accuracy of SCFL is improved by about 3.13％～16.03％under the Non-IID data distribution,and the overall running time is improved by about 3～6 times.Mean while,the security of information transmission is guaranteed at any stage,satisfying the design goals of accuracy,security and efficiency.关键词
联邦学习/隐私保护/聚类/四元数/零共享/秘密共享Key words
federated learning/privacy-preserving/clustering/quaternion/zero-sharing/secret sharing分类
信息技术与安全科学引用本文复制引用
李功丽,马婧雯,范云..梯度隐藏的安全聚类与隐私保护联邦学习[J].计算机应用研究,2024,41(6):1851-1861,11.基金项目
河南省科技攻关计划资助项目(232102211057) （232102211057）
