| Title | A Deep Learning Approach for Anomaly Detection in Industrial Control Systems |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Doraswamy, B., Krishna, K. Lokesh |
| Conference Name | 2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS) |
| Date Published | nov |
| Keywords | anomaly detection, convolutional neural networks, Deep Learning, ICS Anomaly Detection, industrial control, industrial control systems, integrated circuits, intrusion detection system, pubcrawl, resilience, Resiliency, Safety, Scalability, security, signature detection, Support vector machines |
| Abstract | An Industrial Control System (ICS) is essential in monitoring and controlling critical infrastructures such as safety and security. Internet of Things (IoT) in ICSs allows cyber-criminals to utilize systems' vulnerabilities towards deploying cyber-attacks. To distinguish risks and keep an eye on malicious activity in networking systems, An Intrusion Detection System (IDS) is essential. IDS shall be used by system admins to identify unwanted accesses by attackers in various industries. It is now a necessary component of each organization's security governance. The main objective of this intended work is to establish a deep learning-depended intrusion detection system that can quickly identify intrusions and other unwanted behaviors that have the potential to interfere with networking systems. The work in this paper uses One Hot encoder for preprocessing and the Auto encoder for feature extraction. On KDD99 CUP, a data - set for network intruding, we categorize the normal and abnormal data applying a Deep Convolutional Neural Network (DCNN), a deep learning-based methodology. The experimental findings demonstrate that, in comparison with SVM linear Kernel model, SVM RBF Kernel model, the suggested deep learning model operates better. |
| DOI | 10.1109/ICAISS55157.2022.10011054 |
| Citation Key | doraswamy_deep_2022 |
A Deep Learning Approach for Anomaly Detection in Industrial Control Systems