报告详情
  1. 活动首页
  2. 报告清单
  3. 报告详情
Server-Side Adaptive Trimming Policy to Defend Against Data Poisoning Attacks in Federated Learning
编号：131 访问权限：仅限参会人 更新：2025-12-23 13:12:31 浏览：101次 拓展类型2

报告开始：2025年12月29日 15:30（Asia/Amman）

报告时间：15min

所在会场：[S4] Track 4: Dedicated Technologies for Wireless Networks Track 6: Signal Processing for Wireless Communications Track 8: Communication and Networking Technologies for Smart Agriculture [S4] Track 4: Dedicated Technologies for Wireless NetworksTrack 6: Signal Processing for Wireless CommunicationsTrack 8: Communication and Networking Technologies for Smart Agriculture

视频 无权播放 演示文件

提示：该报告下的文件权限为仅限参会人，您尚未登录，暂时无法查看。

摘要
Federated Learning (FL) enables a decentralized approach of training machine learning, deep learning models without gathering data in a central repository, thereby preserving data privacy. However, FL remains vulnerable to data poisoning attacks, where poisonous clients hold corrupted data and transmit malicious updates. The contribution of these malicious updates during server-side aggregation not only degrade the accuracy of the global model but also slow down its convergence and cause significant fluctuations in accuracy across communication rounds. In this work, we propose a server-side adaptive trimming (SSAT) policy to defend against data poisoning attacks. Experimental results on the MNIST dataset with a simulated label-flipping attack demonstrate that our proposed method outperforms a baseline approach against data poisoning attacks, i.e., trimmed mean, by reducing accuracy fluctuations across communication rounds and effectively detecting malicious updates in each round.
 
关键词
Federated Learning, Data Poisoning, Adaptive Trimming, Label-Flipping attack, Accuracy Fluctuations
报告人
Uddalok Sen
Lecturer India；Dept. of Information Technology MCKV Institute of Enginnering Howrah

稿件作者
Uddalok Sen India；Dept. of Information Technology MCKV Institute of Enginnering Howrah
Debaleena Datta Dept. of Computer Science & Applications Techno Main Saltlake
Mohamed Hafez INTI-IU-University;Shinawatra University
Ayman Amer Faculty of Engineering； Jordan； Zarqa Univeristy
Mohammad Tahidul Islam School of IT and Engineering Melbourne Institute of Technology Melbourne, Australia
Muhammad Fazal Ijaz Australia；Torrens University
发表评论
验证码 看不清楚，更换一张
全部评论
重要日期

  • 会议日期

    12月29日

    2025

    至

    12月31日

    2025

  • 12月30日 2025

    报告提交截止日期

  • 02月10日 2026

    初稿截稿日期

  • 02月10日 2026

    注册截止日期

主办单位
国际科学联合会
承办单位
扎尔卡大学
联系方式
登录查看完整联系方式
历届会议
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询