Enhancing IoT Security with Activity-Based Attack Modeling and Hybrid Classification Techniques

Abstract

The proliferation of Internet of Things (IoT) devices in industrial environments (Industrial IoT or IIoT) has brought about significant advancements in automation and data analytics. However, the integration of these devices also introduces new security vulnerabilities, making them prime targets for cyber-attacks. This study aims to enhance the security of IIoT systems by employing an activity-based attack modeling approach coupled with hybrid classification techniques. Our proposed method leverages a hybrid GRU-LSTM model to detect and mitigate security threats in real-time. Activity-based attack modeling involves the analysis of device behavior and the identification of deviations from normal activity patterns. By focusing on the contextual behavior of IIoT devices, we can more accurately detect anomalies indicative of potential security breaches. The hybrid GRU-LSTM model, which combines the strengths of Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) networks, is utilized to process the sequential data generated by IIoT devices. This combination enhances the model's ability to capture both short-term and long-term dependencies in the data, improving the detection accuracy of complex attack patterns. Our experimental results demonstrate that the proposed hybrid GRU-LSTM model achieves an impressive accuracy rate of 98.18% in identifying various types of cyber-attacks on IIoT systems. The implementation of this model at the edge of IIoT networks ensures real-time threat detection and response, minimizing the latency and reducing the dependency on centralized cloud computing resources. In conclusion, this research presents a robust and efficient approach to enhancing IIoT security through the integration of activity-based attack modeling and advanced hybrid classification techniques. The high accuracy of the proposed method highlights its potential for widespread adoption in securing IIoT environments against evolving cyber threats. This work contributes to the growing body of knowledge in IoT security and paves the way for further innovations in protecting industrial systems from cyber-attacks.