Optimising Intrusion Detection in Cyber-Physical Systems

The application of digital twin or model in industries are recently used as a means for enhancing operational efficiency of Cyber-Physical Systems (CPSs). However, this comes with challenges bordering mostly around detection of cyber-attacks using replication as a means. This study considers a synthetic digital object dataset and its physical object equivalent for intrusion detection using Principal Component Analysis (PCA) and autoencoder for dimensionality reduction. Application of random forest and XGBoost machine learning on both objects to compare the performance on the two objects. To fill a methodological gap, the study implemented the developed model on the digital object dataset and its physical object equivalent to assess intrusion detention capability. The study established that the application of the developed random forest model on the use case digital object dataset varies slightly from its physical equivalent as assessed using standard performance metrics, though revealing very good performance for both objects, which validates the digital object and its applicability in the real world.