Industrial control systems (ICSs) are vital to critical infrastructure in energy, manufacturing, and other industries. As ICSs become increasingly interconnected, their complexity grows, making them more vulnerable to cyber attacks and system failures. This growing complexity underscores the critical need for advanced anomaly detection techniques to ensure the safe and reliable operation of ICSs. To address this need, we propose a novel method, the physical process and controller graph attention network (PCGAT), which constructs multi-level graphs based on physical process and controller information. Experiments on two real-world ICS datasets demonstrate that PCGAT achieves superior performance and enables the localization of anomalies within specific physical processes. Moreover, by leveraging graph attention networks (GATs), PCGAT enhances interpretability in anomaly detection.

In view of the problems existing in the current teaching of computer network technology and application course, this paper introduces the educational concept driven by innovative thinking into the teaching of the course, and puts forward specific teaching reform measures: the teaching method which adopts the engineering application of innovative thinking as the guidance and focuses the problems on the core knowledge points, combining MOOC, SPOC and flipped classroom teaching philosophy, it is student-centered and arouses students’ interest in learning. Practice has proved that the teaching reform has obvious practical effects: students can quickly grasp the basic theory of computer network with more goals, and meanwhile, their practical ability, teamwork ability and innovation ability can be better trained and improved, which is conducive to the cultivation of high-quality innovative talents.