Detection of Cyberattacks in Industrial Control Systems Using Enhanced Principal Component Analysis and Hypergraph-Based Convolution Neural Network (EPCA-HG-CNN)

Abstract

The automated operations of industrial control systems (ICSs) highly rely on the interconnected devices, sensors, and actuators that are monitored and controlled by the supervisory control and data acquisition (SCADA) systems. Despite the numerous benefits of unifying the networking technologies with SCADA systems, ICSs are more susceptible to cyberattacks that can disrupt the secure operations of the critical infrastructures. Thus, the design and development of an efficient attack detection approach has become a complex task. Hence, this research work presents a novel hypergraph-based anomaly detection technique with enhanced principal component analysis and convolution neural network (EPCA-HG-CNN) to detect deviant behaviors of such systems. The proposed EPCA-HG-CNN algorithm involves two phases: 1) dimensionality reduction using enhanced PCA and 2) anomaly detection with HG-based CNN. Furthermore, the performance of EPCA-HG-CNN is evaluated with Singapore University of Technology and Design secure water treatment system and the experimental results show that the proposed EPCA-HG-CNN has identified anomalous behavior of the data with high detection rate, low false positives, and better classification accuracy.