A Distribution-Aware Robust Federated Learning Framework for Mobile Edge Networks

Federated learning (FL) is a promising technology for achieving edge intelligence in mobile edge networks while preserving the privacy of local clients. However, a significant challenge in FL is the non-IID data across clients, which can lead to inconsistent updates between local and global models, ultimately hindering convergence. Furthermore, recent research has shown that FL models are susceptible to adversarial attacks, especially in non-IID scenarios, which can significantly impair their performance. This vulnerability poses further challenges to achieving robust and generalizable edge intelligence. In this paper, we first identify that the model’s predictions for classes with fewer samples are less confident compared to those with more samples, even in federated adversarial environments. Second, recognizing that adversarial training (AT) is an effective defense mechanism, we propose a distribution-aware-assisted federated adversarial training to balance the model’s predictions. Specifically, we suggest assigning higher scores to classes with fewer samples and lower scores to those with more samples during each local AT process, thereby improving the global model’s robustness against adversarial attacks. Experimental results on several popular datasets show that our method achieves performance on par with or better than various baseline approaches.