Towards Robust Federated Learning via Logits Calibration on Non-IID Data

arXiv:2403.02803v1 Announce Type: new
Abstract: Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent studies have shown that FL is vulnerable to adversarial examples (AEs), leading to a significant drop in its performance. Meanwhile, the non-independent and identically distributed (non-IID) challenge of data distribution between edge devices can further degrade the performance of models. Consequently, both AEs and non-IID pose challenges to deploying robust learning models at …

abstract adversarial adversarial examples arxiv collaborative cs.cv data devices distributed edge edge networks examples federated learning framework independent management networks performance privacy robust studies training type via vulnerable