Industrial Control Anomaly Detection Based on Distributed Linear Deep Learning

As more and more devices in Cyber-Physical Systems (CPS) are connected to the Internet, physical components such as programmable logic controller (PLC), sensors, and actuators are facing greater risks of network attacks, and fast and accurate attack detection techniques are crucial. The key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time series. To address this issue, we propose an anomaly detection method based on distributed deep learning. Our method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series, which can maintain the edge of discrete features. We use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation set. Our method can not only detect abnormal attacks but also locate the sensors that cause anomalies. We conducted experiments on the Secure Water Treatment (SWAT) and Water Distribution (WADI) public datasets. The experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.