Backdoor Attacks and Defenses in Federated Learning: State-of-the-Art, Taxonomy, and Future Directions
IEEE Wireless Communications · 2023-04 · 30 (2) · 114-121
DOI: 10.1109/mwc.017.2100714 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Wireless Communications, 2023-04. Verfasst von Xueluan Gong und 3 weiteren Autor:innen. Die Arbeit wurde bisher 108-mal zitiert (Crossref) und nennt 15 Literaturangaben. Gefördert von: NSFC, National Natural Science Foundation of China.
Abstract (Originalsprache)
The federated learning framework is designed for massively distributed training of deep learning models among thousands of participants without compromising the privacy of their training datasets. The training dataset across participants usually has heterogeneous data distributions. Besides, the central server aggregates the updates provided by different parties, but has no visibility into how such updates are created. The inherent characteristics of federated learning may incur a severe security concern. The malicious participants can upload poisoned updates to introduce backdoored functionality into the global model, in which the backdoored global model will misclassify all the malicious images (i.e., attached with the backdoor trigger) into a false label but will behave normally in the absence of the backdoor trigger. In this work, we present a comprehensive review of the state-of-the-art backdoor attacks and defenses in federated learning. We classify the existing backdoor attacks into two categories: data poisoning attacks and model poisoning attacks, and divide the defenses into anomaly updates detection, robust federated training, and backdoored model restoration. We give a detailed comparison of both attacks and defenses through experiments. Lastly, we pinpoint a variety of potential future directions of both backdoor attacks and defenses in the framework of federated learning.
Förderung
- NSFC
- National Natural Science Foundation of China
Zitieren
APA
Gong, X., Chen, Y., Wang, Q., & Kong, W. (2023). Backdoor Attacks and Defenses in Federated Learning: State-of-the-Art, Taxonomy, and Future Directions. IEEE Wireless Communications, 30(2), 114-121. https://doi.org/10.1109/mwc.017.2100714
Vancouver
Gong X, Chen Y, Wang Q, Kong W. Backdoor Attacks and Defenses in Federated Learning: State-of-the-Art, Taxonomy, and Future Directions. IEEE Wireless Communications. 2023;30(2):114-121. doi:10.1109/mwc.017.2100714
BibTeX
@article{Gong2023,
author = {Gong, Xueluan and Chen, Yanjiao and Wang, Qian and Kong, Weihan},
title = {Backdoor Attacks and Defenses in Federated Learning: State-of-the-Art, Taxonomy, and Future Directions},
journal = {IEEE Wireless Communications},
year = {2023},
volume = {30},
number = {2},
pages = {114--121},
doi = {10.1109/mwc.017.2100714}
}
EUVIMED