Cyber security and beyond: Detecting malware and concept drift in AI-based sensor data streams using statistical techniques

Abstract

In the Industrial Internet of Things (IIoT), mobile devices can be used to remotely monitor and control industrial processes, equipment, and machinery. They can also be used to optimize production and maintenance processes, improve safety, and increase efficiency in industries such as manufacturing, energy, and transportation. The adoption of IIoT has the potential to increase production and efficiency, but it also raises new cybersecurity concerns since interconnected industrial systems are more susceptible to malware intrusions. Malware attacks on IIoT systems can have grave consequences, including production delays, data loss, and physical asset damage. To aid this we propose to use statistical drift detection methods to perceive any change in data patterns and train the machine learning classifiers to counter newly developed malware samples then and there. Our results with an accuracy of 95.2% and F1-score of 94% indicate that our approach is highly successful and easy to adopt.