Email: asiancomnet@usssociety.org
Website & IT Support: hi@aconf.org
[Online]Server-Side Adaptive Trimming Policy to Defend Against Data Poisoning Attacks in Federated Learning
Server-Side Adaptive Trimming Policy to Defend Against Data Poisoning Attacks in Federated Learning
ID：131
Submission ID：122 View Protection：ATTENDEE
Updated Time：2025-12-23 13:12:31 Hits：299
Online
Start Time：2025-12-29 15:30 （Asia/Amman）
Duration：15min
Session：[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
Video
No Permission
Presentation File
Tips: The file permissions under this presentation are only for participants. You have not logged in yet and cannot view it temporarily.
Abstract
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.
Keywords
Federated Learning, Data Poisoning, Adaptive Trimming, Label-Flipping attack, Accuracy Fluctuations
Speaker
Uddalok Sen
Lecturer India；Dept. of Information Technology MCKV Institute of Enginnering HowrahSubmission Author
All comments
Comment submit