# Delving into the Adversarial Robustness of Federated Learning Source: [Delving into the Adversarial Robustness of Federated Learning]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:01:51.507Z Authors: Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chao Wu Published: 2023-02-19T04:54:25.000Z ## Abstract In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on the challenge of adversarial robustness of federated learning. To facilitate a better understanding of the adversarial vulnerability of the existing FL methods, we conduct comprehensive robustness evaluations on various attacks and adversarial training methods. Moreover, we reveal the negative impacts induced by directly adopting adversarial training in FL, which seriously hurts the test accuracy, especially in non-IID settings. In this work, we propose a novel algorithm called Decision Boundary based Federated Adversarial Training (DBFAT), which consists of two components (local re-weighting and global regularization) to improve both accuracy and robustness of FL systems. Extensive experiments on multiple datasets demonstrate that DBFAT consistently outperforms other baselines under both IID and non-IID settings. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-10 (Adversarial Robustness FGSM, PGD, SparseFool, PAP)](): Image Classification; CIFAR-10; Benign Accuracy: 51.45. - [Image Classification on CIFAR-100 (Adversarial Robustness: BA, FGSM, PGD, SparseFool, PAP)](): Image Classification; CIFAR-100; Benign Accuracy (BA): 23.28. - [Image Classification on STL-10 (test) (Adversarial Robustness)](): Image Classification; STL-10 (test); Accuracy (Benign): 46.79. - [Image Classification Robustness on STL-10 (Adversarial Attacks)](): Image Classification; STL-10; Accuracy (Benign): 42.75. - [Image Classification on GTSRB (test)](): Image Classification; GTSRB (test); Accuracy (Clean): 80.96. - [Robust Image Classification on GTSRB](): Image Classification; GTSRB; Natural Accuracy: 75.4. ## Original sources and implementation [Original paper]() [PDF]()