Machine Learning Methods for Anomaly Detection in Industrial Control Systems
| Title | Machine Learning Methods for Anomaly Detection in Industrial Control Systems |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Tai, J., Alsmadi, I., Zhang, Y., Qiao, F. |
| Conference Name | 2020 IEEE International Conference on Big Data (Big Data) |
| Date Published | Dec. 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-6251-5 |
| Keywords | anomaly detection, Artificial neural networks, boosting, CPS, cyber-physical system security, Deep Learning, ICs, ICS Anomaly Detection, industrial control, industrial control system security, Integrated circuit modeling, machine learning, Neural networks, pubcrawl, random forests, resilience, Resiliency, Scalability, Testing |
| Abstract | This paper examines multiple machine learning models to find the model that best indicates anomalous activity in an industrial control system that is under a software-based attack. The researched machine learning models are Random Forest, Gradient Boosting Machine, Artificial Neural Network, and Recurrent Neural Network classifiers built-in Python and tested against the HIL-based Augmented ICS dataset. Although the results showed that Random Forest, Gradient Boosting Machine, Artificial Neural Network, and Long Short-Term Memory classification models have great potential for anomaly detection in industrial control systems, we found that Random Forest with tuned hyperparameters slightly outperformed the other models. |
| URL | https://ieeexplore.ieee.org/document/9378018 |
| DOI | 10.1109/BigData50022.2020.9378018 |
| Citation Key | tai_machine_2020 |
- industrial control system security
- testing
- Scalability
- Resiliency
- resilience
- random forests
- pubcrawl
- Neural networks
- machine learning
- Integrated circuit modeling
- Anomaly Detection
- industrial control
- ICS Anomaly Detection
- ICs
- deep learning
- cyber-physical system security
- CPS
- boosting
- Artificial Neural Networks