Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data

arXiv:2404.06776v1 Announce Type: new
Abstract: Federated learning (FL) is a privacy-preserving distributed framework for collaborative model training on devices in edge networks. However, challenges arise due to vulnerability to adversarial examples (AEs) and the non-independent and identically distributed (non-IID) nature of data distribution among devices, hindering the deployment of adversarially robust and accurate learning models at the edge. While adversarial training (AT) is commonly acknowledged as an effective defense strategy against adversarial attacks in centralized training, we shed light on …

abstract adversarial adversarial examples arxiv challenges collaborative contrast cs.ai cs.cv cs.lg data deployment devices distributed distribution edge edge networks examples feature federated learning framework however independent nature networks privacy robust training type vulnerability