MACHINE LEARNING ALGORITHMS FOR CYBER ATTACK CLASSIFICATION

Samarov X. . & Barotova Z. .


Annotatsiya

In modern cybersecurity, timely detection of attacks against network infrastructures and their correct classification are of great importance. This study analyzed the effectiveness of five main classifiers based on machine learning - K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM) and Artificial Neural Network (ANN). The study was conducted on the NSL-KDD dataset, where attack types - DoS, Probe, U2R, R2L and Normal traffic classes were used in the detection process. The performance of the model was evaluated based on the criteria of accuracy, precision, recall and F1-score. The results showed that the Random Forest algorithm demonstrated the highest efficiency across all metrics, especially in the DoS and Normal classes. Although SVM performed poorly in the subclasses (U2R and R2L), it maintained overall stability.


Adabiyotlar

  1. Primartha, A. and I. L. Tama. An efficient intrusion detection system for IoT security using CNN decision forest. Electronics 12(24), 4953 (2023). https://doi.org/10.3390/electronics12244953
  2. Kalbhor, M., S. Shinde, D. E. Popescu and D. J. Hemanth. Hybridization of deep learning pre-trained models with machine learning classifiers and fuzzy min–max neural network for cervical cancer diagnosis. Diagnostics 13, 1363 (2023).
  3. J.N. Myhre, K.ØMikalsen,S.Løkse, R.Jenssen, Robust clustering using a kNN mode seeking ensemble. Pattern Recogn. 76, 491–505 (2018)
  4. P. Dollár, C.L. Zitnick, Structured forests for fast edge detection, in Proceedings of the IEEE International Conference on Computer Vision, pp. 1841–1848
  5. L.F. Nicolas-Alonso, J. Gomez-Gil, Brain computer interfaces, a review. Sensors 12(2), 1211 1279
  6. F.M. Bayat, M. Prezioso, B. Chakrabarti, H. Nili, I. Kataeva, D. Strukov, Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nat. Commun. 9(1), 1–7 (2018)
  7. S. Sharma, Activation functions in neural networks. Towards Data Sci. 6
  8. Alsamhi, S. H., N. S. Rajput and M. S. Ansari. Hybrid deep learning model with KNN for intrusion detection system. Computers, Materials & Continua 66(3), 2713–2727 (2020). https://doi.org/10.32604/cmc.2020.012076
  9. D. Dasgupta, Z. Akhtar, and S. Sen, “Machine learning in cybersecurity: a comprehensive survey,” 10.1177/1548512920951275.
  10. P. Odim and R. Shrestha, “Analysis of K-Nearest Neighbor for Network Intrusion Detection,” International Journal of Scientific and Hybrid Research in Engineering (IJSHRE), vol. 10, no. 5, pp. 41–47, 2023. Available: https://ijournals.in/wp-content/uploads/2023/06/6.IJSHRE-110508
  11. R. A. Faizal, H. F. T. Ahmad, and M. H. Jabar, “Intrusion Detection System Using Random Forest on the NSL-KDD Dataset,” in Proc. Int. Conf. on Electrical Engineering and Informatics (ICEEI), IEEE, 2019, pp. 1–6. Available: https://www.researchgate.net/publication/335718695
  12. S. H. Shah and S. U. Rehman, “A Comparative Study of Intrusion Detection Systems Applied to NSL-KDD Dataset,” in Proc. Int. Conf. on Emerging Trends in Computer Science and Electronics Engineering (ETCSEE), 2022, pp. 45–52. Available: https://www.researchgate.net/publication/357762378
  13. A. Y. Abdullahi, A. S. Alfa, and M. A. Muhammad, “Performance Evaluation of Intrusion Detection System using Selected Features and Machine Learning Classifiers,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 23, no. 3, pp. 1610–1618, 2021. Available: https://www.researchgate.net/publication/352556899
  14. P. S. Vijayarani and S. Sylviaa, “Intrusion Detection System with Customized Machine Learning Techniques for NSL-KDD Dataset,” in Proc. Int. Conf. on Communication and Signal Processing (ICCSP), 2023, pp. 1–6. Available: https://www.researchgate.net/publication/376861280