An IIoT Digital Twin Architecture for Anomaly Traffic Analysis of HWIL Devices Using Neural Network

The Industrial Internet of Things (IIoT) introduces the ever-growing digital risks of cybersecurity into physical environments, leading to a wide range of new vulnerabilities, including threats to public safety, physical harm, and potentially devastating attacks on shared public infrastructure. These security vulnerabilities are prevalent across the Internet of Things (IoT) spectrum, from low-end consumer devices to extensive industrial systems. This paper presents an approach for analyzing Industrial Internet of Things traffic using a neural network to classify normal and malicious traffic. The neural network has been generated in a simulated industrial environment with the Digital Twin (DT) and Hardware in the Loop (HITL) approach. The proposed model was trained and tested on datasets derived from real-world IIoT environments and simulated using OMNeT++. The model's performance was evaluated using various metrics, demonstrating its potential to enhance IIoT security.