ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering

Xu, Jian; Huang, Shao-Lun*; Song, Linqi; Lan, Tian清华大学
42nd IEEE International Conference on Distributed Computing Systems (ICDCS)2022DOI: 10.1109/ICDCS54860.2022.00120
6被引4阅读
引用收藏
分享

摘要

Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e.g., by computing validation error rate) or leverages statistic-based methods (e.g. median and Krum) to identify and remove malicious gradients from Byzantine clients. In this paper, we remark that auxiliary data may not always be available in practice and focus on the statistic-based approach. However, recent work on model poisoning attacks has shown that well-crafted attacks can circumvent most of median- and distance-based statistical defense methods, making malicious gradients indistinguishable from honest ones. To tackle this challenge, we show that the element-wise sign of gradient vector can provide valuable insight in detecting model poisoning attacks. Based on our theoretical analysis of the Little is Enough attack, we propose a novel approach called SignGuard to enable Byzantine-robust federated learning through collaborative malicious gradient filtering. More precisely, the received gradients are first processed to generate relevant magnitude, sign, and similarity statistics, which are then collaboratively utilized by multiple filters to eliminate malicious gradients before final aggregation. Finally, extensive experiments of image and text classification tasks are conducted under recently proposed attacks and defense strategies. The numerical results demonstrate the effectiveness and superiority of our proposed approach.

学科与关键词

关键词
Federated LearningAttack DetectionDistributed Learning Security
相关
加载中…
  • APFed: Anti-Poisoning Attacks in Privacy-Preserving Heterogeneous Federated Learning
    Chen, Xiao; Yu, Haining*; Jia, Xiaohua; Yu, XiangzhanIEEE Transactions on Information Forensics and Security, 2023, 18: 5749-5761.被引 1
  • Breaking Distributed Backdoor Defenses for Federated Learning in Non-IID Settings
    Yang, Jijia*; Shu, Jiangang; Jia, Xiaohua18th IEEE International Conference on Mobility, Sensing and Networking (MSN), ELECTR NETWORK, 2022-12-14 To 2022-12-16.被引 1
  • A Differentially Private Federated Learning Model Against Poisoning Attacks in Edge Computing
    Zhou, Jun; Wu, Nan; Wang, Yisong; Gu, Shouzhen*; Cao, Zhenfu; Dong, Xiaolei; Choo, Kim-Kwang RaymondIEEE Transactions on Dependable and Secure Computing, 2023, 20(3): 1941-1958.被引 10
查看全部 →

会议信息

会议名称
42nd IEEE International Conference on Distributed Computing Systems (ICDCS)
会议日期
2022-07-10 至 2022-07-13
论文集名
2022 IEEE 42ND INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2022)
发表日期
2022
起止页码
1223-1235
DOI
10.1109/ICDCS54860.2022.00120
资助标注
Shenzhen Science and Technology Program [KQTD20170810150821146]; National Key R&D Program of China [2021YFA0715202]; High-end Foreign Expert Talent Introduction Plan [G2021032013L]; Hong Kong RGC grant [ECS 21212419]; InnoHK initiative; Government of the HKSAR; Laboratory for AI-Powered Financial Technologies
收录
ISTP

作者

  • X

    Xu, Jian (第一作者)

    tsinghua univ

  • H

    Huang, Shao-Lun (通讯)

    tsinghua univ

查看全部 4 位作者收起作者
  • S

    Song, Linqi

  • L

    Lan, Tian

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417