Anomaly Detection in Cyber Physical Systems Using Recurrent Neural Networks

This paper presents a novel unsupervised approach to detect cyber attacks in Cyber-Physical Systems (CPS). We describe an unsupervised learning approach using a Recurrent Neural network which is a time series predictor as our model. We then use the Cumulative Sum method to identify anomalies in a replicate of a water treatment plant. The proposed method not only detects anomalies in the CPS but also identifies the sensor that was attacked. The experiments were performed on a complex dataset which is collected through a Secure Water Treatment Testbed (SWaT). Through the experiments, we show that the proposed technique is able to detect majority of the attacks designed by our research team with low false positive rates.