A Model-Free Stealthy Attack for Cyber-Physical Systems Based on Deep Reinforcement Learning
IEEE Transactions on Systems, Man, and Cybernetics: Systems · 2025-07 · 55 (7) · 5091-5101
DOI: 10.1109/tsmc.2025.3559710 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2025-07. Verfasst von Qirui Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic Research Program of Jiangsu, Postgraduate Research & Practice Innovation Program of Jiangsu Province.
Abstract (Originalsprache)
This article, from the attacker’s standpoint, develops a model-free stealthy attack that can steer the system state to the predefined target value and evade detection, without prior knowledge of the system dynamics. A constrained Markov decision process (CMDP) is first modeled to characterize the objective of the stealthy attack. On the basis of the established CMDP, an actor-critic reinforcement learning algorithm is proposed to train the attacker’s policy. Furthermore, by introducing a Lyapunov function constructed from the action value function to the algorithm, convergence of the attacked system’s state to the target is theoretically guaranteed. Differing from existing model-free stealthy attacks which are only suitable for linear systems, the proposed approach guarantees the applicability to nonlinear systems. A linear numerical example and a nonlinear example of flotation industrial system are provided to validate the effectiveness of our proposed stealthy attack.
Förderung
- National Natural Science Foundation of China
- Basic Research Program of Jiangsu
- Postgraduate Research & Practice Innovation Program of Jiangsu Province
- Graduate Innovation Program of China University of Mining and Technology
Zitieren
APA
Zhang, Q., Meng, S., Dai, W., Xia, Z., Yang, C., & Wang, X. (2025). A Model-Free Stealthy Attack for Cyber-Physical Systems Based on Deep Reinforcement Learning. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 55(7), 5091-5101. https://doi.org/10.1109/tsmc.2025.3559710
Vancouver
Zhang Q, Meng S, Dai W, Xia Z, Yang C, Wang X. A Model-Free Stealthy Attack for Cyber-Physical Systems Based on Deep Reinforcement Learning. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2025;55(7):5091-5101. doi:10.1109/tsmc.2025.3559710
BibTeX
@article{Zhang2025,
author = {Zhang, Qirui and Meng, Siqi and Dai, Wei and Xia, Zhenxing and Yang, Chunyu and Wang, Xuesong},
title = {A Model-Free Stealthy Attack for Cyber-Physical Systems Based on Deep Reinforcement Learning},
journal = {IEEE Transactions on Systems, Man, and Cybernetics: Systems},
year = {2025},
volume = {55},
number = {7},
pages = {5091--5101},
doi = {10.1109/tsmc.2025.3559710}
}
EUVIMED