基于零信任机制的联邦学习模型  

Federated Learning Model Based on Zero Trust Mechanism

作　　者：龚颖 许文韬 赵策 王斌君[1] GONG Ying;XU Wen-tao;ZHAO Ce;WANG Bin-jun(Information Network Security College,People's Public Security University of China,Beijing 100240,China)

机构地区：[1]中国人民公安大学信息网络安全学院,北京100240

出　　处：《科学技术与工程》2024年第19期8166-8175,共10页Science Technology and Engineering

基　　金：国家社会科学基金(20AZD114)。

摘　　要：为使联邦学习能够满足更高的安全与效率需求,提出了一种采取双重加密与批处理加密方法的零信任模型。首先,利用双重加密防范来自服务器与其他参与方的多方威胁,且通过选取不同的加密方式并设置加密顺序,保证联邦学习模型在更安全的情况下正常运转;其次,在双重加密的基础上引入批处理模块,通过以密钥位数为依据的拆分再拼接操作,提升加密的效率,保证联邦学习模型在更高效的情况下正常运转。理论分析与实验结果表明:所提出的零信任机制的联邦学习模型能够防范来自多方的推理攻击,并维持与单层同态加密相近的开销。可见零信任机制在联邦学习中的应用具备相当程度的可行性,能够同时满足高安全性、高效率的需求。In order to enable federated learning to meet higher security and efficiency requirements,a zero trust model using double encryption and batch encryption was proposed.Firstly,double encryption was used to prevent multi-party threats from the server and other participants.By selecting different encryption methods and setting the encryption order,the federated learning model can be guaranteed to operate normally in a more secure environment.Secondly,the batch processing module was introduced on the basis of double encryption.Through splitting and splicing operations based on the number of key bits,the efficiency of encryption was improved to ensure the normal operation of the federated learning model in a more efficient manner.Theoretical analysis and experimental results show that the proposed federated learning model of zero trust mechanism can prevent inference attacks from multiple parties,and maintain the overhead similar to that of single-layer homomorphic encryption.It can be seen that the application of zero trust mechanism in federated learning has a certain degree of feasibility,and can meet the requirements of high security and high efficiency at the same time.

关 键 词：联邦学习 零信任 双重加密 批处理加密 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]