As digitalization expands, Industrial Control Systems (ICS) face increasing cybersecurity threats. This project aim to addresses this by developing a self-learning security solution for ICS. Utilizing machine learning, the system learns “normal” operational patterns, detecting anomalies indicative of cyberattacks. Additionally, pattern recognition techniques identify communication data threats. An important aspect of the approach is to making machine learning’s decision-making transparent and comprehensible, empowering users with meaningful insights. In this project, we are collaborating with the Fraunhofer (IOSB-INA) and the Rhebo GmbH.