EUVIMEDEUVIMED entdecken
Crossref

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning

Yujing Wang, Hainan Zhang, Sijia Wen, Wangjie Qiu, Binghui Guo

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (24) · 25443-25451

DOI: 10.1609/aaai.v39i24.34733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yujing Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning is susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic attacks. When facing advanced attacks, their defense stability is notably insufficient. Therefore, it is imperative to develop adaptive defenses against such advanced poisoning attacks. We find that benign clients exhibit significantly higher data distribution stability than malicious clients in federated learning in both CV and NLP tasks. Therefore, the malicious clients can be recognized by observing the stability of their data distribution. In this paper, we propose AdaAggRL, an RL-based Adaptive Aggregation method, to defend against sophisticated poisoning attacks. Specifically, we first utilize distribution learning to simulate the clients' data distributions. Then, we use maximum mean discrepancy (MMD) to calculate the pairwise similarity of the current local model data distribution, its historical data distribution, and global model data distribution. Finally, we use policy learning to adaptively determine the aggregation weights based on the above similarities. Experiments on four real-world datasets demonstrate that the proposed defense model significantly outperforms widely adopted defense models for sophisticated attacks.

Zitieren

APA

Wang, Y., Zhang, H., Wen, S., Qiu, W., & Guo, B. (2025). Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24), 25443-25451. https://doi.org/10.1609/aaai.v39i24.34733

Vancouver

Wang Y, Zhang H, Wen S, Qiu W, Guo B. Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(24):25443-25451. doi:10.1609/aaai.v39i24.34733

BibTeX
@article{Wang2025,
  author = {Wang, Yujing and Zhang, Hainan and Wen, Sijia and Qiu, Wangjie and Guo, Binghui},
  title = {Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {24},
  pages = {25443--25451},
  doi = {10.1609/aaai.v39i24.34733}
}
Kostenlos starten →