Fake or Compromised? Making Sense of Malicious Clients in Federated Learning

arXiv:2403.06319v1 Announce Type: new
Abstract: Federated learning (FL) is a distributed machine learning paradigm that enables training models on decentralized data. The field of FL security against poisoning attacks is plagued with confusion due to the proliferation of research that makes different assumptions about the capabilities of adversaries and the adversary models they operate under. Our work aims to clarify this confusion by presenting a comprehensive analysis of the various poisoning attacks and defensive aggregation rules (AGRs) proposed in the …

abstract arxiv assumptions attacks capabilities cs.cr cs.lg data decentralized decentralized data distributed fake federated learning machine machine learning making paradigm poisoning attacks research security sense training training models type