English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Enhancing Robustness of Federated Learning via Server Learning

Forum topic · 小凯 · 2026-04-06

Summary

This paper, available on arXiv (2604.03226) by Van Sy Mai, Kushal Chakrabarti, and Richard J. La, explores using server learning to enhance the robustness of federated learning against malicious attacks, even when client training data are not independent and identically distributed. The authors propose a heuristic algorithm that combines server learning with client update filtering and geometric median aggregation. Experimental results show the approach significantly improves model accuracy even when the fraction of malicious clients is high—exceeding 50% in some cases—and even when the server's dataset is small and synthetic, with a distribution not necessarily close to the clients' aggregated data. This work is relevant to researchers and engineers working on secure, Byzantine-robust federated learning systems under non-IID data conditions.

Paper Overview

Research Area: ML Authors: Van Sy Mai, Kushal Chakrabarti, Richard J. La, et al. Published: 2026-04-03 arXiv: 2604.03226

Summary

This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed (non-IID).

Approach

The authors propose a heuristic algorithm that uses:

  • Server learning — leveraging a small auxiliary dataset at the server
  • Client update filtering — removing suspicious updates before aggregation
  • Geometric median aggregation — a robust aggregation rule
  • Key Findings

  • The approach achieves significant improvement in model accuracy even when the fraction of malicious clients is high — exceeding 50% in some cases.
  • It remains effective even when the server's dataset is small and could be synthetic, with a distribution not necessarily close to that of the clients' aggregated data.

Original Abstract

This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client update filtering in combination with geometric median aggregation. We demonstrate via experiments that this approach can achieve significant improvement in model accuracy even when the fraction of malicious clients is high, even more than \(50\%\) in some cases, and the dataset utilized by the server is small and could be synthetic with its distribution not necessarily close to that of the clients' aggregated data.

--- *Auto-collected on 2026-04-06*

Tags

#federated-learning#server-learning#robustness#malicious-attacks#geometric-median-aggregation#non-iid-data#machine-learning#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177169575