Two-phase Defense Against Poisoning Attacks on Federated Learning-based Intrusion Detection
Computers & Security · 2023-06 · 129 · 103205
DOI: 10.1016/j.cose.2023.103205 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers & Security, 2023-06. Verfasst von Yuan-Cheng Lai und 6 weiteren Autor:innen. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
the local models of attackers and benign participants are quite different. The second phase tests the aggregated model with the dataset and tries to find the attackers when its accuracy is low. Experiment results show that DPA-FL can reach 96.5% accuracy in defending against poisoning attacks. Compared with other defense mechanisms, DPA-FL can improve F1-score by 20 ∼ 64% under backdoor attacks. Also, DPA-FL can exclude the attackers within twelve rounds when the attackers are few.
Zitieren
APA
Lai, Y., Lin, J., Lin, Y., Hwang, R., Lin, P., Wu, H., & Chen, C. (2023). Two-phase Defense Against Poisoning Attacks on Federated Learning-based Intrusion Detection. Computers & Security, 129, 103205. https://doi.org/10.1016/j.cose.2023.103205
Vancouver
Lai Y, Lin J, Lin Y, Hwang R, Lin P, Wu H, et al. Two-phase Defense Against Poisoning Attacks on Federated Learning-based Intrusion Detection. Computers & Security. 2023;129:103205. doi:10.1016/j.cose.2023.103205
BibTeX
@article{Lai2023,
author = {Lai, Yuan-Cheng and Lin, Jheng-Yan and Lin, Ying-Dar and Hwang, Ren-Hung and Lin, Po-Chin and Wu, Hsiao-Kuang and Chen, Chung-Kuan},
title = {Two-phase Defense Against Poisoning Attacks on Federated Learning-based Intrusion Detection},
journal = {Computers & Security},
year = {2023},
volume = {129},
pages = {103205},
doi = {10.1016/j.cose.2023.103205}
}
EUVIMED