В настоящей статье рассматривается применение многослойного перцептрона (MLP) для классификации сетевого трафика с целью обнаружения киберугроз. Модель была обучена на датасете NSL-KDD, который является стандартом для задач выявления атак и широко используется в исследованиях. В ходе экспериментов была проведена предварительная обработка данных, включающая кодирование категориальных признаков
и балансировку классов методом SMOTE для устранения дисбаланса между нормальным и вредоносным трафиком. Результаты показали высокую точность классификации?– 96.64 % – даже в условиях формирования шума и 10-кратной кросс-валидации, что подтверждает надежность предложенного подхода. В статье предложены показатели эффективности, такие как точность, полнота и F1-мера, которые могут служить основой для дальнейших исследований и оптимизации моделей машинного обучения для повышения безопасности сетей.
1.??Sommer R., Paxson V. Outside the closed world: on using machine learning for network intrusion detection // 2010 IEEE Symposium on Security and Privacy.?– IEEE, 2010. – P. 305–316. – DOI: 10.1109/SP.2010.25.
2.??Roesch M. Snort: lightweight intrusion detection for networks // Proceedings of the 13th USENIX Conference on System Administration (LISA '99). – USENIX, 1999. – P. 229–238.
3.??Fuzziness based semi-supervised learning approach for intrusion detection system / R.A.R. Ashfaq, X.Z. Wang, J.Z. Huang, H. Abbas, Y.L. He // Information Sciences. – 2017. – Vol. 378. – P. 484–497.
4.??A deep learning approach to network intrusion detection / N. Shone, T.N. Ngoc, V.D. Phai, Q. Shi // IEEE Transactions on Emerging Topics in Computational Intelligence. – 2018. – Vol. 2 (1). – P. 41–50.
5.??Intrusion detection system: a comprehensive review / H.J. Liao, C.H.R. Lin, Y.C. Lin, K.Y. Tung // Journal of Network and Computer Applications. – 2013. – Vol. 36 (1). – P. 16–24.
6.??Bhuyan M.H., Bhattacharyya D.K., Kalita J.K. Network anomaly detection: methods, systems and tools // IEEE Communications Surveys & Tutorials. – 2014.?– Vol. 16 (1). – P. 303–336.
7.??A deep learning approach for network intrusion detection system / A. Javaid, Q. Niyaz, W. Sun, M. Alam // Proceedings of the 9th EAI International Conference on Bio-inspired Information and Communications Technologies. – ACM, 2016. – P. 21–26.
8.??Vinayakumar R., Soman K.P., Poornachandran P. Applying deep learning approaches for network traffic classification and intrusion detection // 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). – IEEE, 2017. – P. 1222–1228.
9.??Aggarwal C.C. Neural networks and deep learning: a textbook. – Springer, 2018.
10.??Goodfellow I., Bengio Y., Courville A. Deep learning. – MIT Press, 2016.
11.??Akbar K.A.C., Varma P.M. Intrusion detection system based on multi-layer perceptron neural networks // International Journal of Computer Applications. – 2012. – Vol. 52 (7). – P. 25–30.
12.??Ahmed M.S.S. Intrusion detection system using MLP neural network with packet statistical features // Journal of Communications Software and Systems. – 2019. – Vol. 15 (3). – P. 267–274.
13.??Goodfellow I., Bengio Y., Courville A. Deep learning. – MIT Press, 2016.
14.??Nielsen M.A. Neural networks and deep learning. – Determination Press, 2015.
15.??Deep learning approach for intelligent intrusion detection system / R. Vinayakumar, M. Alazab, K.P. Soman, P. Poornachandran, S. Venkatraman // IEEE Access. – 2019. – Vol. 7. – P. 41525–41550.
16.??Method of intrusion detection using deep neural network / Y. Kim, J. Lee, Y. Kim, H.K. Kim // 2017 International Conference on Big Data and Smart Computing (BigComp). – IEEE, 2018. – P. 313–316.
17.??Li Y., Wang Y. A hybrid malicious code detection method based on deep learning // International Journal of Security and Its Applications. – 2018. – Vol. 12 (2). – P. 71–82.
18.??Network traffic classifier with convolutional and recurrent neural networks for internet of things / M. López-Martín, B. Carro, A. Sánchez-Esguevillas, J. Lloret // IEEE Access. – 2017. – Vol. 5. – P. 18042–18050.
19.??Chiu W.Y., Tsai Y.H., Li M.H. Improving network intrusion detection by the time-related features // 2015 IEEE International Conference on Applied System Innovation (ICASI). – IEEE, 2015. – P. 997–1000.
20.??Bishop C.M. Pattern recognition and machine learning. – Springer, 2006.
21.??A detailed analysis of the KDD CUP 99 data set / M. Tavallaee, E. Bagheri, W. Lu, A.A. Ghorbani // Proceedings of the 2009 IEEE Symposium on Computational Intelligence in Security and Defense Applications. – IEEE, 2009. – DOI: 10.1109/CISDA.2009.5356528.
22.??Han J., Kamber M., Pei J. Data mining: concepts and techniques. – 3rd ed. – Morgan Kaufmann, 2012.
23.??SMOTE: synthetic minority over-sampling technique / N.V. Chawla, K.W. Bowyer, L.O. Hall, W.P. Kegelmeyer // Journal of Artificial Intelligence Research. – 2002. – Vol. 16. – P. 321–357.
24.??Zhang J., Li W., Liu Z. Enhancing intrusion detection using noise injection in deep neural networks // Security and Communication Networks. – 2018. – Art. 6725018.
25.??Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection // Artificial Intelligence. – 1995. – Vol. 14 (2). –
P. 1137–1143.
26.??Bishop C.M. Training with noise is equivalent to Tikhonov regularization // Neural Computation. – 1995. – Vol. 7 (1). – P. 108–116.
27.??Aggarwal C.C. Outlier analysis. – 2nd ed. – Springer, 2016.
28.??Box G.E., Jenkins G. M., Reinsel G.C. Time series analysis: forecasting and control. – 5th ed. – Wiley, 2015.
29.??Hsu C.W., Chang C.C., Lin C.J. A practical guide to support vector classification. Technical Report. – National Taiwan University, 2010.
30.??Ng A.Y. Feature selection, L1 vs. L2 regularization, and rotational invariance // Proceedings of the 21st International Conference on Machine Learning (ICML). – ACM, 2004. – P. 615–622.
31.??Generative adversarial nets / I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio // Advances in Neural Information Processing Systems (NeurIPS). – Montreal, 2014.
Подсевалов А.Г., Киселев М.А., Иванов А.В. Применение нейронной сети Multilayer Perceptron (MLP) для обнаружения и классификации киберугроз в сетевом трафике // Безопасность цифровых технологий. – 2024. – № 4 (115). – С. 37–65. – DOI: 10.17212/
2782-2230-2024-4-37-65.
Podsevalov A.G., Kiselev M.A., Ivanov A.V. Primenenie neironnoi seti Multilayer Perceptron (MLP) dlya obnaruzheniya i klassifikatsii kiberugroz v setevom trafike [Application of Multilayer Perceptron (MLP) neural network for detection and classification of cyber threats in network traffic]. Bezopasnost' tsifrovykh tekhnologii = Digital Technology Security, 2024, no. 4 (115), pp. 37–65. DOI: 10.17212/2782-2230-2024-4-37-65.