Abstract
With the steady growth in the adoption of IoT in an industrial context, security challenges intensify. Security threats to IoT devices in a nuclear plant or an oil refinery are much higher risk compared to home appliances. In this paper, we present an explainable, efficient, and highly accurate machine-learning based intrusion detection system for industrial IoT, referred to as E2I3DS. This work successfully reduces the needed features within the WUSTL-IIOT-2021 dataset from 48 features to 11 only, while maintaining very high accuracy. Experiments utilizing the 11-feature dataset showed that proposed system has a higher accuracy of 99.97%, with a false positive rate of 0.01% and a false negative rate of 0.04%. The proposed system also proved to be very efficient with an excellent detection time of 0.1517 μs. In addition, the model was explained using Shapley additive explanations.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
