MFIR: Model-Free Intrusion Response for Partially Observable Industrial Control Systems
IEEE Internet of Things Journal · 01.07.2026 · 13 (13) · 29588-29599
DOI: 10.1109/jiot.2026.3685344 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.07.2026. Verfasst von Yingxu Lai und 2 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The increasing number of multistage attacks has brought severe cybersecurity threats to industrial control system (ICS), making it crucial to develop autonomous and effective intrusion response systems (IRSs). Most existing IRS approaches depend on the idealized assumption that the system state is perfectly known and directly available for intelligent control decisions. However, this assumption is rarely satisfied in practice, as state information is typically incomplete and only partially observable, which severely limits the applicability and effectiveness of these methods. To address this challenge, we propose a model-free intrusion response (MFIR) approach tailored to ICS with partially observable states. We formulate intrusion response as a partially observable Markov decision process (MDP) and construct a simulated ICS with incomplete state observations. Then, we use a recurrent neural network to infer the hidden complete states from historical observation sequences, thereby avoiding reliance on prior knowledge such as transition or observation probabilities. Based on the inferred states, we develop a deep reinforcement learning (RL) algorithm with a dual-branch neural network to make response decisions. Experiments on a Tennessee Eastman-based ICS testbed demonstrate that MFIR outperforms existing approaches, achieving up to 32.86% higher total reward, fewer compromised nodes, and lower defense cost under various observability levels. These results verify that the proposed approach is well-suited for intrusion response in partially observable ICS environments.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Lai, Y., Zhao, P., & Wang, Z. (2026). MFIR: Model-Free Intrusion Response for Partially Observable Industrial Control Systems. IEEE Internet of Things Journal, 13(13), 29588-29599. https://doi.org/10.1109/jiot.2026.3685344
Vancouver
Lai Y, Zhao P, Wang Z. MFIR: Model-Free Intrusion Response for Partially Observable Industrial Control Systems. IEEE Internet of Things Journal. 2026;13(13):29588-29599. doi:10.1109/jiot.2026.3685344
BibTeX
@article{Lai2026,
author = {Lai, Yingxu and Zhao, Peng and Wang, Ziqi},
title = {MFIR: Model-Free Intrusion Response for Partially Observable Industrial Control Systems},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {13},
pages = {29588--29599},
doi = {10.1109/jiot.2026.3685344}
}
EUVIMED