Robust Multiagent Reinforcement Learning for UAV Systems: Countering Byzantine Attacks
Information · 19.11.2023 · 14 (11) · 623
DOI: 10.3390/info14110623 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 19.11.2023. Verfasst von Jishu K. Medhi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Multiple unmanned aerial vehicle (multi-UAV) systems have gained significant attention in applications, such as aerial surveillance and search and rescue missions. With the recent development of state-of-the-art multiagent reinforcement learning (MARL) algorithms, it is possible to train multi-UAV systems in collaborative and competitive environments. However, the inherent vulnerabilities of multiagent systems pose significant privacy and security risks when deploying general and conventional MARL algorithms. The presence of even a single Byzantine adversary within the system can severely degrade the learning performance of UAV agents. This work proposes a Byzantine-resilient MARL algorithm that leverages a combination of geometric median consensus and a robust state update model to mitigate, or even eliminate, the influence of Byzantine attacks. To validate its effectiveness and feasibility, the authors include a multi-UAV threat model, provide a guarantee of robustness, and investigate key attack parameters for multiple UAV navigation scenarios. Results from the experiments show that the average rewards during a Byzantine attack increased by up to 60% for the cooperative navigation scenario compared with conventional MARL techniques. The learning rewards generated by the baseline algorithms could not converge during training under these attacks, while the proposed method effectively converged to an optimal solution, proving its viability and correctness.
Zitieren
APA
Medhi, J. K., Liu, R., Wang, Q., & Chen, X. (2023). Robust Multiagent Reinforcement Learning for UAV Systems: Countering Byzantine Attacks. Information, 14(11), 623. https://doi.org/10.3390/info14110623
Vancouver
Medhi JK, Liu R, Wang Q, Chen X. Robust Multiagent Reinforcement Learning for UAV Systems: Countering Byzantine Attacks. Information. 2023;14(11):623. doi:10.3390/info14110623
BibTeX
@article{Medhi2023,
author = {Medhi, Jishu K. and Liu, Rui and Wang, Qianlong and Chen, Xuhui},
title = {Robust Multiagent Reinforcement Learning for UAV Systems: Countering Byzantine Attacks},
journal = {Information},
year = {2023},
volume = {14},
number = {11},
pages = {623},
doi = {10.3390/info14110623}
}
EUVIMED