考虑外部敌手的去中心化联邦学习梯度聚合协议  

Decentralized Federated Learning Gradient Aggregation Protocol Considering External Adversaries

作　　者：邹洁丽 张子华 高铁杠[1] ZOU Jie-Li;ZHANG Zi-Hua;GAO Tie-Gang(College of Software,Nankai University,Tianjin 300350,China)

机构地区：[1]南开大学软件学院,天津300350

出　　处：《计算机系统应用》2025年第3期14-26,共13页Computer Systems & Applications

基　　金：天津市自然科学基金重点项目(21JCZDJC00130)。

摘　　要：联邦学习是一种分布式机器学习技术,允许参与方在本地训练模型并上传更新至中央服务器,由中央服务器聚合更新来生成更优的全局模型,从而保障数据隐私和解决数据孤岛问题.然而,梯度聚合过程依赖中央服务器,这可能导致单点故障,且中央服务器也是潜在的恶意攻击者.因此,联邦学习必须去中心化.现有的去中心化方案没有考虑外部敌手和数据通信带来的性能瓶颈问题.为了解决上述问题,提出一种考虑外部敌手的去中心化联邦学习方法.该方法应用Shamir秘密共享方案,将模型更新分成多个份额,保护梯度隐私.该方法提出一种洪泛共识协议,每轮随机选取某一参与方作为中央服务器完成全局聚合,高效实现联邦学习的去中心化.同时,该方法引入BLS聚合签名,防范外部敌手攻击,提升验证效率.理论分析和实验结果表明,该方法是安全高效的,相比同类联邦学习方法具有更高的效率.Federated learning is a distributed machine learning technique that allows participants to train models locally and upload updates to a central server.The central server aggregates the updates to generate a better global model,ensuring data privacy and solving the problem of data silos.However,the gradient aggregation relies on a central server,which may lead to a single point of failure,and the central server is also a potential malicious attacker.Therefore,federated learning needs to be decentralized.The existing decentralized solutions ignore external adversaries and the performance bottlenecks issues caused by data communication.To address the above issues,this study proposes a decentralized federated learning method considering external adversaries.The method applies Shamir’s secret sharing scheme to divide model updates into multiple shares to protect gradient privacy.The method proposes a flooding consensus protocol that randomly selects a participant as the central server in each round to complete global aggregation,efficiently achieving the decentralization of federated learning.At the same time,the method introduces BLS aggregate signatures to prevent external adversary attacks and improve verification efficiency.Theoretical analysis and experimental results indicate that this method is safe and efficient,having higher efficiency than similar federated learning methods.

关 键 词：联邦学习 Shamir秘密共享 共识协议 BLS聚合签名 去中心化 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]