Blockchain-based Deep Learning Models for Intrusion Detection in Industrial Control Systems: Frameworks and Open Issues

Devi Priya V.S., Sibi Chakkaravarthy Sethuraman, Muhammad Khurram Khan,
Blockchain-based Deep Learning Models for Intrusion Detection in Industrial Control Systems: Frameworks and Open Issues,
Journal of Network and Computer Applications,
Volume 243,
2025,
104286,
ISSN 1084-8045,
https://doi.org/10.1016/j.jnca.2025.104286.
(https://www.sciencedirect.com/science/article/pii/S1084804525001833)
Abstract: Critical infrastructure and industrial systems are both becoming more and more networked and equipped with computing and communications tools. To manage processes and automate them where possible, Industrial Control Systems (ICS) manage a variety of components, including monitoring tools and software platforms. More complicated data is now being run on the networks, including data(past), money(present), and brains (future). In order to predictably detect specific services and patterns (deep learning) and automatically check authenticity and transfer value (blockchain), deep learning and blockchain are integrated into the ICS network. Hence, we conducted a thorough examination of the models published in the literature in order to comprehend how to integrate machine learning and blockchain efficiently and successfully for intrusion detection services. We also provide useful guidance for future research in this area by noting significant issues that must be addressed before substantial deployments of IDS models in ICS.
Keywords: Industrial Control Systems; Cybersecurity; Intrusion detection systems; Machine learning; Deep learning; Blockchain