A NEW APPROACH TO INTELLIGENT NETWORK TRAFFIC FLOW ANALYSIS
Kabulov A. . & Juraev M. .
Annotatsiya
Today, modern cyber threats are highly developed and new types are emerging, and the demand for systems aimed at detecting them in the protection of critical network infrastructure is also increasing. Rules-based systems have trouble detecting new threats as they emerge. Organizations are trying to use artificial intelligence-based threat detection methods as a solution. This research paper presents a method that detects network changes with artificial intelligence. Machine learning (ML) and deep learning (DL) methods, such as Support Vector Machines (SVM), Random Forest (RF), Autoencoders and Convolutional Neural Networks (CNNs), were used. The selected attribute based on the SHapley Additive Explanations (SHAP) analysis is used to identify the most important features in network traffic and is used to verify the understandability and effectiveness of the model. The proposed model achieved an accuracy of 80.4%, F1-score of 89.1%. Comparative analysis with previous studies has proven to provide high accuracy in detecting unexpected situations.
Adabiyotlar
- Ahmad, I., Basheri, M., Iqbal, M. J., & Rahim, A. (2018). Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection. IEEE access, 6, 33789-33795.
- Al-Qatf, M., Lasheng, Y., Al-Habib, M., & Al-Sabahi, K. (2018). Deep learning approach combining sparse autoencoder with SVM for network intrusion detection. Ieee Access, 6, 52843-52856.
- Neupane, S., Ables, J., Anderson, W., Mittal, S., Rahimi, S., Banicescu, I., and Seale, M., “Explainable Intrusion Detection Systems (X-IDS): A survey of current methods, challenges, and opportunities,” IEEE Access, vol. 10, pp. 112392–112415, 2022. doi: 10.1109/ACCESS.2022.3216617.
- M. Ahsan and K. Nygard, “Convolutional neural networks with LSTM for intrusion detection,” ResearchGate Preprint, 2020, doi:10.13140/RG.2.2.24796.82567.
- M. Ahsan and K. Nygard, “Convolutional neural networks with LSTM for intrusion detection,” ResearchGate Preprint, 2020, doi:10.13140/RG.2.2.24796.82567.
- Khan, L. U., Yaqoob, I., Tran, N. H., Kazmi, S. A., Dang, T. N., & Hong, C. S. (2020). Edge-computing-enabled smart cities: A comprehensive survey. IEEE Internet of Things journal, 7(10), 10200-10232.
- R. Lazzarini, H. Tianfield, and V. Charissis, “Federated learning for IoT intrusion detection,” AI, vol. 4, no. 3, pp. 509–530, 2023, doi:10.3390/ai4030028.
- A. Aldweesh, A. Derhab, and A. Z. Emam, “Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues,” Knowledge-Based Systems, vol. 189, p. 105124, Jan. 2020, doi:10.1016/j.knosys.2019.105124.
- Aldweesh, A., Derhab, A., & Emam, A. Z. (2020). Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues. Knowledge-Based Systems, 189, 105124.
- Zhuo, S., Hong, Y. Y., & Palaoag, T. D. (2022, December 14). AN INTELLIGENT CYBER SECURITY DETECTION AND RESPONSE PLATFORM. International Journal for Research in Advanced Computer Science and Engineering, 8(12), 1–10. https://doi.org/10.53555/cse.v8i12.2167