Predicting Cybersecurity Threats in Critical Infrastructure for Industry 4.0: A Proactive Approach Based on Attacker Motivations
Adel Alqudhaibi, Majed Albarrak, Abdulmohsan Aloseel, Sandeep Jagtap, Konstantinos Salonitis
Abstract
In Industry 4.0, manufacturing and critical systems require high levels of flexibility and resilience for dynamic outcomes. Industrial Control Systems (ICS), specifically Supervisory Control and Data Acquisition (SCADA) systems, are commonly used for operation and control of Critical Infrastructure (CI). However, due to the lack of security controls, standards, and proactive security measures in the design of these systems, they have security risks and vulnerabilities. Therefore, efficient and effective security solutions are needed to secure the conjunction between CI and I4.0 applications. This paper predicts potential cyberattacks and threats against CI systems by considering attacker motivations and using machine learning models. The approach presents a novel cybersecurity prediction technique that forecasts potential attack methods, depending on specific CI and attacker motivations. The proposed model's accuracy in terms of False Positive Rate (FPR) reached 66% with the trained and test datasets. This proactive approach predicts potential attack methods based on specific CI and attacker motivations, and doubling the trained data sets will improve the accuracy of the proposed model in the future.