Browse by author
Lookup NU author(s): Dr Mujeeb AhmedORCiD
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
© 2026 The Author(s). IET Cyber-Physical Systems: Theory & Applications published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. The security of industrial control systems (ICSs) is crucial due to their integral role in critical national infrastructure. This study tackles the escalating challenges posed by sophisticated cyberattacks, especially those that are unknown and evade existing detection mechanisms. Despite extensive research, there is a notable gap in systematically comparing supervised and unsupervised learning models for anomaly detection, leading to inconsistent evaluations of their effectiveness. To bridge this gap, we developed a comprehensive anomaly detection framework to systematically evaluate these models, focusing on their capability to detect unknown attacks. Utilising operational data from the Secure Water Treatment (SWaT) testbed, we assessed six unsupervised and five supervised learning methods. Our findings reveal significant performance disparities: supervised models excel in precision but have higher undetected rates, whereas unsupervised models achieve superior recall at the expense of increased false alarm rates. This study provides critical insights into the strengths and limitations of both approaches, guiding the development of more robust ICS security solutions.
Author(s): Wang Z, Umer MA, Zhang H, Hassan NU, Ahmed CM
Publication type: Article
Publication status: Published
Journal: IET Cyber-Physical Systems: Theory and Applications
Year: 2026
Volume: 11
Issue: 1
Online publication date: 05/01/2026
Acceptance date: 10/12/2025
Date deposited: 19/01/2026
ISSN (electronic): 2398-3396
Publisher: John Wiley and Sons Inc.
URL: https://doi.org/10.1049/cps2.70037
DOI: 10.1049/cps2.70037
Data Access Statement: The data supporting the findings of this study are available from the iTrust Center at Singapore University of Technology and Design upon request.
Altmetrics provided by Altmetric
