FedRDF: A Robust and Dynamic Aggregation Function against Poisoning Attacks in Federated Learning

arXiv:2402.10082v1 Announce Type: new
Abstract: Federated Learning (FL) represents a promising approach to typical privacy concerns associated with centralized Machine Learning (ML) deployments. Despite its well-known advantages, FL is vulnerable to security attacks such as Byzantine behaviors and poisoning attacks, which can significantly degrade model performance and hinder convergence. The effectiveness of existing approaches to mitigate complex attacks, such as median, trimmed mean, or Krum aggregation functions, has been only partially demonstrated in the case of specific attacks. Our study …

abstract advantages aggregation arxiv attacks concerns cs.cr cs.lg deployments dynamic federated learning function machine machine learning performance poisoning attacks privacy robust security type vulnerable