journal article·2023-03-26Open access

Anomaly Detection Method for Unknown Protocols in a Power Plant ICS Network with Decision Tree

Kyoung-Mun Lee, Min-Yang Cho, Jung-Gu Kim, Kyung-Ho Lee

Applied Sciences· Volume 13· Issue 7

Abstract

This study aimed to enhance the stability and security of power plant control network systems by developing detectable models using artificial intelligence machine learning techniques. Due to the closed system operation policy of facility manufacturers, it is challenging to detect and respond to security threats using standard security systems. With the increasing digitization of control systems, the risk of external malware penetration is also on the rise. To address this, machine learning techniques were applied to extract patterns from network traffic data produced at an average of 6.5 TB per month, and fingerprinting was used to detect unregistered terminals accessing the control network. By setting a threshold between transmission amounts and attempts using one month of data, an anomaly judgment model was learned to define patterns of data communication between the origin and destination. The hypothesis was tested using machine learning techniques if a new pattern occurred and no traffic occurred. The study confirmed that this method can be applied to not only plant control systems but also closed-structured control networks, where availability is critical, and other industries that use large amounts of traffic data. Experimental results showed that the proposed model outperformed existing models in terms of detection efficiency and processing time.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Network Security and Intrusion Detection · Smart Grid Security and Resilience · Anomaly Detection Techniques and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Korea Southern Power Co., Ltd., Andog-si 36618, Republic of Korea

Department of Information Security, Korea University, Seoul 02841, Republic of Korea

Department of Computer Science and Engineering, Korea University, Seoul 02841, Republic of Korea

Department of Computer Software, Dong Seoul University, Seongnam-si 13117, Republic of Korea

Department of AI Application Software, Dong Seoul University, Seongnam-si 13117, Republic of Korea

References (45)

Show source-provided references
1. A review on islanding operation and control for distribution network connected with small hydro power plant10.1016/j.rser.2011.06.010 ↗
2. Network traffic analysis and SCADA security
3. Lippmann, R., Fried, D., Piwowarski, K., and Streilein, W. (2003, January 19–22). Passive operating system identification from TCP/IP packet headers. Proceedings of the Workshop on Data Mining for Computer Security, Melbourne, FL, USA.
4. Automatic payload signature update system for classification of recent network applications
5. Tracking the source of cascading cyber attack traffic using network traffic analysis
6. A survey of automatic protocol reverse engineering tools10.1145/2840724 ↗
7. Borisov, N., Brumley, D., Wang, H.J., Dunagan, J., Joshi, P., and Guo, C. (March, January 28). Generic application-level protocol analyzer and its language. Proceedings of the NDSS Symposium 2007: The Network and Security Conference, San Diego, CA, USA.
8. Caselli, M., Hadžiosmanović, D., Zambon, E., and Kargl, F. (2013, January 16–18). On the feasibility of device fingerprinting in industrial control systems. Proceedings of the 8th International Workshop on Critical Information Infrastructures Security, Amsterdam, The Netherlands.10.1007/978-3-319-03964-0_14 ↗
9. Winston, P.H. (1992). Artificial intelligence, Addison-Wesley Longman Publishing Co., Inc.. [3rd ed.].
10. Matsuda, W., Fujimoto, M., Aoyama, T., and Mitsunaga, T. (2019, January 19–21). Cyber security risk assessment on industry 4.0 using ICS testbed with AI and Cloud. Proceedings of the 2019 IEEE Conference on Application, Information and Network Security (AINS), Pulau Pinang, Malaysia.10.1109/AINS47559.2019.8968698 ↗
11. Yılmaz, E.N., Sayan, H.H., Üstünsoy, F., Gönen, S., Sindiren, E., and Karacayılmaz, G. (2019, January 20–22). ICS Cyber attack analysis and a new diagnosis approach. Proceedings of the ICAIAME 2019: The International Conference on Artificial Intelligence and Applied Mathematics in Engineering, Manavgat, Antalya, Turkey.10.1007/978-3-030-36178-5_11 ↗
12. Cyber security meets artificial intelligence: A survey10.1631/FITEE.1800573 ↗
13. Veiga, A.P. (2018). Applications of artificial intelligence to network security. arXiv.
14. Frank, J. (1994, January 11–14). Artificial intelligence and intrusion detection: Current and future directions. Proceedings of the 17th National Computer Security Conference, Baltimore, MD, USA.
15. A fuzzy k-nearest neighbor algorithm10.1109/TSMC.1985.6313426 ↗
16. Support vector machine classification on the web10.1093/bioinformatics/btg461 ↗
17. A survey of decision tree classifier methodology10.1109/21.97458 ↗
18. Random forest classifier for remote sensing classification10.1080/01431160412331269698 ↗
19. The random forest algorithm for statistical learning10.1177/1536867X20909688 ↗
20. A land use regression model for ambient ultrafine particles in Montreal, Canada: A comparison of linear regression and a machine learning approach10.1016/j.envres.2015.12.016 ↗
21. A review on linear regression comprehensive in machine learning10.38094/jastt1457 ↗
22. Multinomial logistic regression algorithm10.1007/BF00048682 ↗
23. Survey of clustering algorithms10.1109/TNN.2005.845141 ↗
24. Hohman, F., Wongsuphasawat, K., Kery, M.B., and Patel, K. (2020, January 25–30). Understanding and visualizing data iteration in machine learning. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA.10.1145/3313831.3376177 ↗
25. Weinberger, K.Q., and Saul, L.K. (2006, January 16–20). An introduction to nonlinear dimensionality reduction by maximum variance unfolding. Proceedings of the Twenty-First National Conference on Artificial Intelligence and the Eighteenth Innovative Applications of Artificial Intelligence Conference, Boston, MA, USA.
26. Thabtah, F., Cowling, P., and Peng, Y. (2005, January 6). MCAR: Multi-class classification based on association rule. Proceedings of the 3rd ACS/IEEE International Conference on Computer Systems and Applications, Cairo, Egypt.
27. Yoon, S., and Kim, K.J. (2017, January 22–25). Deep Q networks for visual fighting game AI. Proceedings of the 2017 IEEE Conference on Computational Intelligence and Games (CIG), New York, NY, USA.10.1109/CIG.2017.8080451 ↗
28. Chen, T., Niu, W., Xiang, Y., Bai, X., Liu, J., Han, Z., and Li, G. (2018). Gradient band-based adversarial training for generalized attack immunity of A3C path finding. arXiv.
29. (2023, February 02). Scikit-Learn (Choosing the Right Estimator). Available online: https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html.
30. SinFP, unification of active and passive operating system fingerprinting10.1007/s11416-008-0107-z ↗
31. Beverly, R. (2004, January 19–20). A robust classifier for passive TCP/IP fingerprinting. Proceedings of the Passive and Active Network Measurement: 5th International Workshop, PAM 2004, Juan-Les-Pins, France.10.1007/978-3-540-24668-8_16 ↗
32. Conti, G., and Abdullah, K. (2004, January 29). Passive visual fingerprinting of network attack tool. Proceedings of the VizSEC/DMSEC ’04: 2004 ACM Workshop on Visualization and Data Mining for Computer Security, Washington, DC, USA.10.1145/1029208.1029216 ↗
33. Laštovička, M., and Filakovskỷ, D. (2018, January 23–27). Passive OS fingerprinting prototype demonstration. Proceedings of the NOMS 2018—2018 IEEE/IFIP Network Operations and Management Symposium, Taipei, Taiwan.10.1109/NOMS.2018.8406128 ↗
34. Flow whitelisting in SCADA networks10.1016/j.ijcip.2013.08.003 ↗
35. The promise of whitelisting10.1016/S1353-4858(09)70085-6 ↗
36. Erickson, D., Casado, M., and McKeown, N. (2008, January 21–22). The Effectiveness of Whitelisting: A User-Study. Proceedings of the CEAS 2008: The Fifth Conference on Email and Anti-Spam, Mountain View, CA, USA.
37. Application whitelisting: Approaches and challenges
38. Perales Gómez, Á.L., Fernández Maimó, L., Huertas Celdrán, A., and García Clemente, F.J. (2020). Madics: A methodology for anomaly detection in industrial control systems. Symmetry, 12.10.3390/sym12101583 ↗
39. Mokhtari, S., Abbaspour, A., Yen, K.K., and Sargolzaei, A. (2021). A machine learning approach for anomaly detection in industrial control systems based on measurement data. Electronics, 10.10.3390/electronics10040407 ↗
40. DAICS: A deep learning solution for anomaly detection in industrial control systems
41. Anomaly detection for industrial control system based on autoencoder neural network10.1155/2020/8897926 ↗
42. Cao, Y., Zhang, L., Zhao, X., Jin, K., and Chen, Z. (2022). An Intrusion Detection Method for Industrial Control System Based on Machine Learning. Information, 13.10.3390/info13070322 ↗
43. Sommer, R., and Paxson, V. (2010, January 16–19). Outside the closed world: On using machine learning for network intrusion detection. Proceedings of the 2010 IEEE Symposium on Security and Privacy, NW Washington, DC, USA.10.1109/SP.2010.25 ↗
44. Theoretical analysis of an alphabetic confusion matrix10.3758/BF03213026 ↗
45. Visa, S., Ramsay, B., Ralescu, A.L., and Van Der Knaap, E. (2011, January 16–17). Confusion matrix-based feature selection. Proceedings of the MAICS 2011: 22nd Midwest Artificial Intelligence and Cognitive Science Conference, Cincinnati, OH, USA.