Graph Convolutional Network-Based Suspicious Communication Pair Estimation for Industrial Control Systems

This course aims to teach learners how to estimate suspicious communication pairs in industrial control systems using a Graph Convolutional Network (GCN)-based approach. The course covers the background and scope of Deep Convolutional Networks (DCN) and GCN, as well as the process of estimating abnormality scores and evaluating the performance of the model. The course is designed for cybersecurity professionals and individuals interested in network security in industrial settings. The teaching method involves presenting key ideas, explaining the GCN scope and process, discussing the scoring phase, and analyzing experimental results to assess discrimination performance and computational cost.