Hybrid cyber threats detection using explainable AI in Industrial IoT

Abstract

The rise of new technologies has enabled the combination of multiple cyber threats to become more sophisticated and capable cyber attacks, which can result in significant losses and consequences. This work aims to develop a hybrid threat detection system using explainable artificial intelligence techniques, preventing the growing number of combined cyber-attacks in IoT environments. A multilayer hybrid cyber threats model was proposed to analyse increasingly complicated and capable cyber attacks. In addition, an explainable artificial intelligence (XAI) model was designed to create an understandable interpretation for the detection model. The experimental results demonstrate the effectiveness of the proposed hybrid cyber threats analysis model and XAI model.