Anomaly-based Intrusion Detection System for ICS

Industrial Control Systems (ICS) become a crucial target for hackers as these devices are unsupported in terms of storage, complex computations, and security. On the other hand, providing security for these devices are very difficult. Because small downtime of these devices will lead to financial loss and reputation loss for the industry. Sometimes, even it may lead to a disaster. We should also ensure that there are no heavy workloads present in this Operational Technology (OT) network. Hence, the intrusion detection systems for ICS should operate with high levels of accuracy utilizing resources as low as possible. In this paper, an anomaly-based ICS intrusion detection system is proposed. The proposed model uses Pearson Correlation for feature selection and Deep Neural Network for detection. The suggested solution is put to the test using an HIL-based Augmented ICS security dataset. The results show that the proposed model has a good fit and achieves a higher accuracy rate.