FAT: Federated Adversarial Training
Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evasion threats on ML models. In this paper, we take the first known steps towards federated adversarial training (FAT) combining both methods to reduce the threat of evasion during inference while preserving the data privacy during training. We investigate the effectiveness of the FAT protocol for idealised federated settings using MNIST, Fashion-MNIST, and CIFAR10, and provide first insights on stabilising the training on the LEAF benchmark dataset which specifically emulates a federated learning environment. We identify challenges with this natural extension of adversarial training with regards to achieved adversarial robustness and further examine the idealised settings in the presence of clients undermining model convergence. We find that Trimmed Mean and Bulyan defences can be compromised and we were able to subvert Krum with a novel distillation based attack which presents an apparently "robust" model to the defender while in fact the model fails to provide robustness against simple attack modifications.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessFederated LearningSimilar Papers 제목 키워드 기반
$\alpha$-Weighted Federated Adversarial Training
Federated Adversarial Training (FAT) helps us address the data privacy and governance issues, meanwhile maintains the model robustness to the adversarial attack. However, the inner-maximization optimization of Adversaria…
Adversarial AttackFederated LearningCombating Exacerbated Heterogeneity for Robust Models in Federated Learning
Privacy and security concerns in real-world applications have led to the development of adversarially robust federated models. However, the straightforward combination between adversarial training and federated learning …
Federated LearningFADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices
Federated adversarial training can effectively complement adversarial robustness into the privacy-preserving federated learning systems. However, the high demand for memory capacity and computing power makes large-scale …
Adversarial RobustnessFederated LearningPrivacy PreservingDelving into the Adversarial Robustness of Federated Learning
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 …
Adversarial RobustnessFederated LearningDynamic Defense Against Byzantine Poisoning Attacks in Federated Learning
Federated learning, as a distributed learning that conducts the training on the local devices without accessing to the training data, is vulnerable to Byzatine poisoning adversarial attacks. We argue that the federated l…
Data PoisoningFederated LearningImage Classification