Develope novel security metric using Deep-Learning to detect anomaly attacks into the critical infrastructure systems. This metric will be tested by Secure Water Treatment (SWaT) Dataset.
1D (time) Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) are used to detect anomalous attacks into Industrial Control System (ICS). The proposed models have been implemented by using Google’s TensorFlow framework version 2.x and the Keras library.