ICS Anomaly Detection Based on Sensor Patterns and Actuator Rules in Spatiotemporal Dependency

• Published in: IEEE transactions on industrial informatics Vol. 20; no. 8; pp. 10647 - 10656
• Main Authors: Cai, Jun, Wei, Zeheng, Luo, Jianzhen
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Actuators; Anomalies; Anomaly detection; Control systems; cyber-physical system (CPS); Data models; graph neural network (GNN); Graph neural networks; industrial control system; Industrial electronics; Integrated circuit modeling; Knowledge based engineering; Prediction models; Sensors; Spatiotemporal data; Spatiotemporal phenomena; Topology; topology construction

Data-driven methods, such as deep learning, are widely adopted to detect cyberattacks for Industrial control systems (ICSs). Due to the neglect of entity spatial relationships (ESR), however, there is a potential discrepancy between the learned device topology and the real physical process. Meanwhil...