《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (3): 798-808.DOI: 10.11772/j.issn.1001-9081.2025030357

• 网络空间安全 • 上一篇    下一篇

联邦学习在隐私安全领域面临的威胁综述

郗恩康1,2,3, 范菁1,2,3(), 金亚东1,2,3, 董华1,2,3, 俞浩1,2,3, 孙伊航1,2,3   

  1. 1.云南民族大学 电气信息工程学院,昆明 650504
    2.云南省无人自主系统重点实验室(云南民族大学),昆明 650504
    3.云南省高校信息与通信安全灾备重点实验室(云南民族大学),昆明 650504
  • 收稿日期:2025-04-08 修回日期:2025-05-12 接受日期:2025-05-16 发布日期:2025-05-27 出版日期:2026-03-10
  • 通讯作者: 范菁
  • 作者简介:郗恩康(2000—),男,山东枣庄人,硕士研究生,CCF会员,主要研究方向:联邦学习、隐私安全
    金亚东(1998—),男,云南曲靖人,硕士研究生,CCF会员,主要研究方向:联邦学习、信息安全
    董华(2001—),男,山西运城人,硕士研究生,CCF会员,主要研究方向:联邦学习、隐私安全
    俞浩(2000—),男,湖北咸宁人,硕士研究生,CCF会员,主要研究方向:异构联邦学习
    孙伊航(2001—),男,河南许昌人,硕士研究生,CCF会员,主要研究方向:联邦学习、通信优化。
  • 基金资助:
    国家自然科学基金资助项目(12361104);教育部-新一代信息技术创新项目(2023IT077);云南省教育厅科学研究基金资助项目(2025Y0670);云南省教育厅科学研究基金资助项目(2023Y0499);CCF?深信服“远望”科研基金资助项目(CCF-SANGFOR OF 20240210);云南省吴中海专家工作站项目(202305AF150045)

Review of threats faced by federated learning in privacy and security field

Enkang XI1,2,3, Jing FAN1,2,3(), Yadong JIN1,2,3, Hua DONG1,2,3, Hao YU1,2,3, Yihang SUN1,2,3   

  1. 1.School of Electrical and Information Technology,Yunnan Minzu University,Kunming Yunnan 650504,China
    2.Yunnan Key Laboratory of Unmanned Autonomous System (Yunnan Minzu University),Kunming Yunnan 650504,China
    3.Key Laboratory of Information and Communication Security and Disaster Recovery in Universities of Yunnan Province (Yunnan Minzu University),Kunming Yunnan 650504,China
  • Received:2025-04-08 Revised:2025-05-12 Accepted:2025-05-16 Online:2025-05-27 Published:2026-03-10
  • Contact: Jing FAN
  • About author:XI Enkang, born in 2000, M. S. candidate. His research interests include federated learning, privacy security.
    JIN Yadong, born in 1998, M. S. candidate. His research interests include federated learning, information security.
    DONG Hua, born in 2001, M. S. candidate. His research interests include federated learning, privacy security.
    YU Hao, born in 2000, M. S. candidate. His research interests include heterogeneous federated learning.
    SUN Yihang, born in 2001, M. S. candidate. His research interests include federated learning, communication optimization.
  • Supported by:
    National Natural Science Foundation of China(12361104);Ministry of Education — New Generation of Information Technology Innovation Project(2023IT077);Yunnan Provincial Department of Education Scientific Research Fund Project(2025Y0670);CCF-SANGFOR “FarSight” Research Fund(CCF-SANGFOR OF 20240210);Wu Zhonghai Expert Workstation Project of Yunnan Province(202305AF150045)

摘要:

作为一种新型的分布式机器学习,联邦学习在解决数据孤岛和隐私保护问题上具有一定潜力,然而它面临着潜在的隐私威胁和安全威胁。因此,系统性综述联邦学习在隐私与安全领域的前沿研究成果,详细阐述联邦学习的基本概念和工作流程,并对联邦学习中的隐私和安全问题在现有前沿的研究成果上进行分类。首先,分析联邦学习中的隐私威胁,归纳相应的隐私保护方法;其次,总结联邦学习中的安全威胁问题,并介绍相应的安全攻击的防御方法;最后,讨论联邦学习中未来需要解决的挑战,并针对ChatGPT和DeepSeek等大语言模型(LLM)在联邦学习中的应用,进一步探讨LLM带来的计算效率瓶颈与隐私泄露挑战。

关键词: 联邦学习, 隐私威胁, 安全威胁, 大语言模型, 分布式机器学习

Abstract:

Federated learning, as a new type of distributed machine learning, has the potential to address data silos and privacy protection issues, but it faces potential privacy and security threats. Therefore, the cutting-edge research achievements of federated learning in privacy and security field were reviewed systematically, the basic concepts and workflow of federated learning were elaborated in detail, and the privacy and security issues in federated learning were classified based on the current cutting-edge research achievements. Firstly, the privacy threats in federated learning were analyzed, and the corresponding privacy protection methods were summarized. Secondly, the security threats in federated learning were summed up, and the corresponding defense methods against security attacks were introduced. Finally, the challenges in federated learning that need to be addressed in the future were discussed, focusing on the applications of Large Language Models (LLMs) such as ChatGPT and DeepSeek in federated learning, and the computational efficiency and privacy leakage challenges brought by LLMs were further explored.

Key words: federated learning, privacy threat, security threat, Large Language Model (LLM), distributed machine learning

中图分类号: