STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

Excerpt

arXiv:2608.14861v1 Announce Type: cross Abstract: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain for existing defense techniques: (1) accurately distinguishing between benign and malicious model updates and (2) effectively mitigating the influence of poisoned model updates during model aggregation. To address these challenges, we propose a novel defense framework against tar