EUVIMEDEUVIMED entdecken
Crossref

Delving into the Adversarial Robustness of Federated Learning

Jie Zhang, Bo Li, Chen Chen, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chao Wu

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (9) · 11245-11253

DOI: 10.1609/aaai.v37i9.26331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jie Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 42-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Zhang, J., Li, B., Chen, C., Lyu, L., Wu, S., Ding, S., & Wu, C. (2023). Delving into the Adversarial Robustness of Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 11245-11253. https://doi.org/10.1609/aaai.v37i9.26331

Vancouver

Zhang J, Li B, Chen C, Lyu L, Wu S, Ding S, et al. Delving into the Adversarial Robustness of Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(9):11245-11253. doi:10.1609/aaai.v37i9.26331

BibTeX
@article{Zhang2023,
  author = {Zhang, Jie and Li, Bo and Chen, Chen and Lyu, Lingjuan and Wu, Shuang and Ding, Shouhong and Wu, Chao},
  title = {Delving into the Adversarial Robustness of Federated Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {9},
  pages = {11245--11253},
  doi = {10.1609/aaai.v37i9.26331}
}
Kostenlos starten →