An Advanced Boundary Protection Control for the Smart Water Network Using Semisupervised and Deep Learning Approaches

• Published in: IEEE internet of things journal Vol. 9; no. 10; pp. 7298 - 7310
• Main Authors: Sharmeen, Shaila, Huda, Shamsul, Abawajy, Jemal, Ahmed, Chuadhry Mujeeb, Hassan, Mohammad Mehedi, Fortino, Giancarlo
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 15.05.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anomaly detection; Computer crime; cyber attack; cyber–physical system; Deep learning; Electric power distribution; Internet of Things; Protocols; Public transportation; Security; Sensors; Supervisory control and data acquisition; supervisory control and data~acquisition (SCADA); Valves; Water distribution; Water engineering; Water treatment; Water treatment plants
• ISSN: 2327-4662; 2327-4662
• DOI: 10.1109/JIOT.2021.3100461

Critical infrastructures across many industries, such as smart water treatment and distribution networks (SWTDNs) and power generation and public transport networks, depend on the supervisory control and data acquisition (SCADA) system. However, being the core component of the critical infrastructures, it has made the SCADA-based SWTDN system an attractive target for cyberattacks. A successful attack on the SCADA will have a devastating impact on an SWTDN in terms of proper operations; therefore, safeguarding the SCADA from cyberattacks is of paramount. With the increasing cyberattacks on SWTDN, both in number and sophistication, the need to detect these attacks early has become a subject of great interest among practitioners and researchers. To this end, we propose a novel strategy, based on a semisupervised approach. Two semisupervised approaches, including unsupervised learning and deep learning-based approaches, have been proposed. The proposed approaches can involve learning dynamic cyberattack patterns from unlabeled data in an SWTDN. We validate the proposed semisupervised approach experimentally using an operational water treatment plant testbed. The proposed approach achieved almost 100% accuracy and substantially outperforms the existing baseline approaches used in this article. The outcome of the experiment is encouraging and demonstrates the potential use of the semisupervised approach for security control in smart water distribution.