Defending against Data Poisoning Attacks in Federated Learning via User Elimination

arXiv:2404.12778v1 Announce Type: new
Abstract: In the evolving landscape of Federated Learning (FL), a new type of attacks concerns the research community, namely Data Poisoning Attacks, which threaten the model integrity by maliciously altering training data. This paper introduces a novel defensive framework focused on the strategic elimination of adversarial users within a federated model. We detect those anomalies in the aggregation phase of the Federated Algorithm, by integrating metadata gathered by the local training instances with Differential Privacy techniques, …

arxiv attacks community cs.cr data data poisoning defending defensive federated federated learning framework integrity novel poisoning poisoning attacks research strategic threaten training training data