Open Access

ARTICLE

An Intelligent Approach for Intrusion Detection in Industrial Control System

Adel Alkhalil^1,*, Abdulaziz Aljaloud¹, Diaa Uliyan¹, Mohammed Altameemi¹, Magdy Abdelrhman^2,3, Yaser Altameemi⁴, Aakash Ahmad⁵, Romany Fouad Mansour⁶

1 Department of Information and Computer Science, College of Computer Science and Engineering, University of Ha’il, Ha’il, 81481, Saudi Arabia
2 Applied College, University of Ha’il, Ha’il, 81481, Saudi Arabia
3 College of Education, New Valley University, El-Kharga, 72511, Egypt
4 College of Art, University of Ha’il, Ha’il, 81481, Saudi Arabia
5 School of Computing and Communications, Lancaster University, Leipzig, 04109, Germany
6 College of Science, New Valley University, El-Kharga, 72511, Egypt

* Corresponding Author: Adel Alkhalil. Email:

Computers, Materials & Continua 2023, 77(2), 2049-2078. https://doi.org/10.32604/cmc.2023.044506

Received 01 August 2023; Accepted 12 October 2023; Issue published 29 November 2023

Abstract

Supervisory control and data acquisition (SCADA) systems are computer systems that gather and analyze real-time data, distributed control systems are specially designed automated control system that consists of geographically distributed control elements, and other smaller control systems such as programmable logic controllers are industrial solid-state computers that monitor inputs and outputs and make logic-based decisions. In recent years, there has been a lot of focus on the security of industrial control systems. Due to the advancement in information technologies, the risk of cyberattacks on industrial control system has been drastically increased. Because they are so inextricably tied to human life, any damage to them might have devastating consequences. To provide an efficient solution to such problems, this paper proposes a new approach to intrusion detection. First, the important features in the dataset are determined by the difference between the distribution of unlabeled and positive data which is deployed for the learning process. Then, a prior estimation of the class is proposed based on a support vector machine. Simulation results show that the proposed approach has better anomaly detection performance than existing algorithms.

---

Keywords

---