defense arXiv Apr 3, 2026 · 5d ago
Van Sy Mai, Kushal Chakrabarti, Richard J. La et al. · National Institute of Standards and Technology · Tata Consultancy Services +2 more
Byzantine-robust federated learning defense using server-side learning and geometric median aggregation, resilient to 50%+ malicious clients
Data Poisoning Attack federated-learning
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.
federated National Institute of Standards and Technology · Tata Consultancy Services · University of Maryland +1 more
ML Security Papers