AI RESEARCH
FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement
arXiv CS.LG
•
ArXi:2605.11122v1 Announce Type: cross Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing defenses suffer from substantial false-positive rates under realistic non-independent and identically distributed (non-IID) data, incorrectly flagging benign clients and degrading model accuracy even when adversaries are correctly identified.