| Title | Applying of Recurrent Neural Networks for Industrial Processes Anomaly Detection |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Alabugin, Sergei K., Sokolov, Alexander N. |
| Conference Name | 2021 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) |
| Date Published | may |
| Keywords | actuator security, anomaly detection, composability, Human Behavior, industrial control systems, integrated circuits, Intrusion detection, Metrics, Predictive models, process control, pubcrawl, Real-time Systems, Recurrent neural networks, Resiliency, Tools, Training |
| Abstract | The paper considers the issue of recurrent neural networks applicability for detecting industrial process anomalies to detect intrusion in Industrial Control Systems. Cyberattack on Industrial Control Systems often leads to appearing of anomalies in industrial process. Thus, it is proposed to detect such anomalies by forecasting the state of an industrial process using a recurrent neural network and comparing the predicted state with actual process' state. In the course of experimental research, a recurrent neural network with one-dimensional convolutional layer was implemented. The Secure Water Treatment dataset was used to train model and assess its quality. The obtained results indicate the possibility of using the proposed method in practice. The proposed method is characterized by the absence of the need to use anomaly data for training. Also, the method has significant interpretability and allows to localize an anomaly by pointing to a sensor or actuator whose signal does not match the model's prediction. |
| DOI | 10.1109/USBEREIT51232.2021.9455060 |
| Citation Key | alabugin_applying_2021 |
Applying of Recurrent Neural Networks for Industrial Processes Anomaly Detection