paper-with-me

홈 › Papers

FAT: Federated Adversarial Training

2020-12-03 · Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Beat Buesser

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.

📄 PDF Abstract BibTeX arXiv:2012.01791

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessFederated Learning

Similar Papers 제목 키워드 기반

$\alpha$-Weighted Federated Adversarial Training

2021-09-29 · Jianing Zhu, Jiangchao Yao, Tongliang Liu, Kunyang Jia 외

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 Learning

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning

2023-03-01 · Jianing Zhu, Jiangchao Yao, Tongliang Liu, Quanming Yao 외

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 Learning

FADE: Enabling Federated Adversarial Training on Heterogeneous Resource-Constrained Edge Devices

2022-09-08 · Minxue Tang, Jianyi Zhang, Mingyuan Ma, Louis DiValentin 외

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 Preserving

Delving into the Adversarial Robustness of Federated Learning

2023-02-19 · Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu 외

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 Learning

Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning

2020-07-29 · Nuria Rodríguez-Barroso, Eugenio Martínez-Cámara, M. Victoria Luzón, Francisco Herrera

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