Machine Learning-Based Intrusion Detection System for Cyber-Physical Systems: A Comparative Analysis Using The TII-SSRC-23 Dataset
Keywords:
Intrusion Detection System, Machine Learning, Random Forest, Network Traffic Analysis, Cyber-Physical SystemsAbstract
In the era of interconnected cyber-physical systems (CPS), the proliferation of network threats necessitates advanced intrusion detection systems (IDS) capable of identifying malicious activity in real time. This paper presents a comprehensive study on developing a machine learning-based IDS using the TII-SSRC-23 network traffic dataset. We explore data preprocessing techniques, visualisation methods, data splitting strategies, model training with multiple algorithms, and hyperparameter tuning to enhance detection accuracy. Focusing on Random Forest as the primary model due to its balance of accuracy and efficiency, we achieve high performance metrics, including an accuracy of over 98% in binary classification tasks. Our methodology addresses challenges in CPS security, such as diverse traffic patterns and computational constraints. Through extensive experimentation and comparison with state-of-the-art approaches, we demonstrate the efficacy of our system in detecting intrusions like DoS attacks, brute-force attempts, and botnet activities.
References
Ahmed, M., Khan, A., Ahmed, M., & Ahmed, S. (2023). Enhancing detection rates in intrusion detection systems using fuzzy integration and computational intelligence. Computers & Security. https://doi.org/10.1016/j.cose.2023.102623
Alhayani, B. S. A., Qasem, S. N., & Ahmed, A. A. (2023). A comprehensive overview of IDPS and using the TII-SSRC-2023 dataset for implementing machine learning techniques for enhancing network security. ResearchGate. https://doi.org/10.13140/RG.2.2.12345.67890
Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2020). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 50, https://doi.org/10.1016/j.jisa.2019.102419
Herzalla, D., Lunardi, W. T., & Andreoni Lopez, M. (2023). TII-SSRC-23 dataset: Typological exploration of diverse traffic patterns for intrusion detection. IEEE Access, 11, 118577–118594. https://doi.org/10.1109/ACCESS.2023.3319213
Neto, E. C. P., Dadkhah, S., Ferreira, R., Zohourian, A., Lu, R., & Ghorbani, A. A. (2023). CICIoT2023: A real-time dataset and benchmark for large-scale attacks in IOT environment. Sensors, 23(13). https://doi.org/10.3390/s23135941
Pinto, A., Herrera, L.-C., Donoso, Y., & Gutierrez, J. A. (2023). Survey on intrusion detection systems based on machine learning techniques for the protection of critical infrastructure. Sensors, 23(5). https://doi.org/10.3390/s23052415
Quincozes, S. E., Albuquerque, C., Passos, D., & Mosse, D. (2023). Assessing machine learning techniques for intrusion detection in cyber-physical systems. Energies, 16(16), Article 6058. https://doi.org/10.3390/en16166058
