梯度隐藏的安全聚类与隐私保护联邦学习OA北大核心CSTPCD

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.