重庆邮电大学学报（自然科学版）2026，Vol.38Issue(1)：12-19,8.DOI:10.3979/j.issn.1673-825X.202501060007
一种高效安全的联邦学习隐私保护方案
An efficient and secure privacy protection scheme for federated learning
摘要
Abstract
A high-efficiency federated learning data aggregation privacy protection scheme is proposed to address the issue of low communication efficiency and inadequate security performance caused by differences in device geographical location,network status,storage capacity,computational capability,and parameter exchange during the federal learning process.This scheme reduces the direct interaction frequency between participating clients and the server by grouping clients and selecting group leaders,utilizes gradient compression techniques to reduce the number of parameters uploaded by clients,and introduces a trusted third party and efficient key protocols to encrypt the parameters uploaded by participants,ensuring their privacy security.Additionally,each user can independently verify the aggregated results returned by the server.Secu-rity analysis indicates that this scheme satisfies indistinguishability and data privacy requirements,and experimental results demonstrate high model accuracy and significant advantages in communication overhead.关键词
联邦学习/隐私保护/组长选取/梯度选择/可验证聚合Key words
federated learning/privacy protection/team leader selection/gradient selection/verifiable aggregation分类
信息技术与安全科学引用本文复制引用
宋成,樊源龙..一种高效安全的联邦学习隐私保护方案[J].重庆邮电大学学报（自然科学版）,2026,38(1):12-19,8.基金项目
国家自然科学基金项目(62273290) National Natural Science Foundation of China(62273290) （62273290）
