FedDefender: Client-Side Attack-Tolerant Federated Learning

被引:10
|
作者
Park, Sungwon [1 ]
Han, Sungwon
Wu, Fangzhao [2 ]
Kim, Sundong [3 ]
Zhu, Bin [2 ]
Xie, Xing [2 ]
Cha, Meeyoung [1 ,4 ]
机构
[1] Korea Adv Inst Sci & Technol, Daejeon, South Korea
[2] Microsoft Res Asia, Beijing, Peoples R China
[3] GIST, Gwangju, South Korea
[4] Inst for Basic Sci Korea, Daejeon, South Korea
关键词
Federated Learning; Client-Side Defense; Model Poisoning Attack; Knowledge Distillation; Meta Learning;
D O I
10.1145/3580305.3599346
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Federated learning enables learning from decentralized data sources without compromising privacy, which makes it a crucial technique. However, it is vulnerable to model poisoning attacks, where malicious clients interfere with the training process. Previous defense mechanisms have focused on the server-side by using careful model aggregation, but this may not be effective when the data is not identically distributed or when attackers can access the information of benign clients. In this paper, we propose a new defense mechanism that focuses on the client-side, called FedDefender, to help benign clients train robust local models and avoid the adverse impact of malicious model updates from attackers, even when a server-side defense cannot identify or remove adversaries. Our method consists of two main components: (1) attack-tolerant local meta update and (2) attack-tolerant global knowledge distillation. These components are used to find noise-resilient model parameters while accurately extracting knowledge from a potentially corrupted global model. Our client-side defense strategy has a flexible structure and can work in conjunction with any existing server-side strategies. Evaluations of real-world scenarios across multiple datasets show that the proposed method enhances the robustness of federated learning against model poisoning attacks.
引用
收藏
页码:1850 / 1861
页数:12
相关论文
共 50 条
  • [31] A client-side workflow middleware in the grid
    Li, Y
    Zhu, QM
    Li, MG
    Chen, Y
    NETWORKING - ICN 2005, PT 1, 2005, 3420 : 19 - 26
  • [32] Client-side Mobile Visual Search
    Hartl, Andreas
    Schmalstieg, Dieter
    Reitmayr, Gerhard
    PROCEEDINGS OF THE 2014 9TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, THEORY AND APPLICATIONS (VISAPP 2014), VOL 3, 2014, : 125 - 132
  • [33] Mining client-side activity for personalization
    Fenstermacher, KD
    Ginsburg, M
    WECWIS 2002: FOURTH IEEE INTERNATIONAL WORKSHOP ON ADVANCED ISSUES OF E-COMMERCE AND WEB-BASED INFORMATION SYSTEMS, PROCEEDINGS, 2002, : 205 - 212
  • [34] Client-side dynamic preprocessing of transactions
    Jurk, S
    Neiling, M
    ADVANCES IN DATABASES AND INFORMATION SYSTEMS, PROCEEDINGS, 2003, 2798 : 103 - 117
  • [35] Client-Side Vulnerabilities in Commercial VPNs
    Bui, Thanh
    Rao, Siddharth
    Antikainen, Markku
    Aura, Tuomas
    SECURE IT SYSTEMS, NORDSEC 2019, 2019, 11875 : 103 - 119
  • [36] Client-Side Detection of Clickjacking Attacks
    Shahriar, Hossain
    Haddad, Hisham M.
    INTERNATIONAL JOURNAL OF INFORMATION SECURITY AND PRIVACY, 2015, 9 (01) : 1 - 25
  • [37] Making client-side image maps
    Horton, RM
    Russell, MJ
    BIOTECHNIQUES, 1998, 25 (01) : 58 - +
  • [38] A cost model for client-side caas
    Sriwiroj, Chaturong
    Banditwattanawong, Thepparit
    Lecture Notes in Electrical Engineering, 2015, 339 : 361 - 368
  • [39] Client-side monitoring for web mining
    Fenstermacher, KD
    Ginsburg, M
    JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY, 2003, 54 (07): : 625 - 637
  • [40] Web Spoofing Prevention: Machine Learning Based Client-Side Defence
    Chanakya, G.
    Spoorthi, Mareddy
    Kumar, Racha Sanjay
    Reddy, Jakka Yashwanth
    Chowdary, B.V.
    Kumar, Reddy Dheeraj
    2nd International Conference on Sustainable Computing and Smart Systems, ICSCSS 2024 - Proceedings, 2024, : 1098 - 1104