Chia-Mei Chen¹, Zheng-Xun Cai¹, Gu-Hsin Lai², ¹National Sun Yat-sen University, Taiwan, ²Taiwan Police College, Taiwan

The “Industry 4.0” revolution and Industry Internet of Things (IIoT) has dramatically transformed how manufacturing and industrial companies operate. Industrial control systems (ICS) process critical function, and the past ICS attacks have caused major damage and disasters in the communities. IIoT devices in an ICS environment communicate in heterogeneous protocols and the attack vectors might exhibit different misbehavior patterns. This study proposes a classification model to detect anomalies in ICS environments. The evaluation has been conducted by using ICS datasets from multiple sources and the results show that the proposed LSTM detection model performs effectively.

Industry Internet of Things, Machine Learning, Anomaly Detection.