DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (9) · 10711-10719
DOI: 10.1609/aaai.v37i9.26271 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Gang Yan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref).
Abstract (Originalsprache)
Federated learning (FL) is known to be susceptible to model poisoning attacks in which malicious clients hamper the accuracy of the global model by sending manipulated model updates to the central server during the FL training process. Existing defenses mainly focus on Byzantine-robust FL aggregations, and largely ignore the impact of the underlying deep neural network (DNN) that is used to FL training. Inspired by recent findings on critical learning periods (CLP) in DNNs, where small gradient errors have irrecoverable impact on the final model accuracy, we propose a new defense, called a CLP-aware defense against poisoning of FL (DeFL). The key idea of DeFL is to measure fine-grained differences between DNN model updates via an easy-to-compute federated gradient norm vector (FGNV) metric. Using FGNV, DeFL simultaneously detects malicious clients and identifies CLP, which in turn is leveraged to guide the adaptive removal of detected malicious clients from aggregation. As a result, DeFL not only mitigates model poisoning attacks on the global model but also is robust to detection errors. Our extensive experiments on three benchmark datasets demonstrate that DeFL produces significant performance gain over conventional defenses against state-of-the-art model poisoning attacks.
Zitieren
APA
Yan, G., Wang, H., Yuan, X., & Li, J. (2023). DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 10711-10719. https://doi.org/10.1609/aaai.v37i9.26271
Vancouver
Yan G, Wang H, Yuan X, Li J. DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(9):10711-10719. doi:10.1609/aaai.v37i9.26271
BibTeX
@article{Yan2023,
author = {Yan, Gang and Wang, Hao and Yuan, Xu and Li, Jian},
title = {DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {9},
pages = {10711--10719},
doi = {10.1609/aaai.v37i9.26271}
}
EUVIMED