Saif Rawashdeh*

Department of Computer Science, Jordan University of Science and Technology, Jordan

*Corresponding Author: Saif Rawashdeh, Department of Computer Science, Jordan University of Science and Technology, Jordan.

Received: October 11, 2023; Published: October 22, 2023

Abstract

Machine learning techniques have been applied in various fields and shown to be effective, like cybersecurity. Machine learning can be used in cybersecurity to detect and defend against network attacks. It can also be used to detect anomalies in system behavior that may indicate an attack is underway. Machine learning is a valuable tool for cybersecurity professionals and can help make systems more secure. This paper aims to develop seven machine learning algorithms (Decision Tree, Random Forest, Gradient Boosting, XGBoost, AdaBoost, Multilayer Perceptron, and Voting) to detect anomaly attacks using a well-known dataset named UNSW-NB15. To assess the performance of these models, there are four popular evaluation metrics: accuracy, precision, recall, and f1-score. Therefore, we applied two experiments and an enchantment experiment to detect several types of attacks: 1) Binary classification into two types of attacks (normal and malicious). 2) Multiclass classification (types of malicious attacks). 3) Enchantment experiment on the second experiment (choose the three most frequent attacks in the dataset out of nine attacks). These experiments are done to see if each algorithm is able to distinguish between the types of malicious attacks in the UNSW_NB15 dataset. The results showed that the voting classifier performed the best in the first experiment. Furthermore, when compared to others, the XGB performed better in the second and enchantment experiments.

Keywords: UNSW_NB15 Dataset; Machine Learning; Cybersecurity Attacks; Detection Attacks

References

1. Seemma PS., et al. “Overview of cyber security”. International Journal of Advanced Research in Computer and Communication Engineering7.11 (2018): 125-128.‏
2. Ervural B C and Ervural B. “Overview of cyber security in the industry 4.0 era”. In Industry 4.0: managing the digital transformation (2018): 267-284.‏
3. Chowdhury A. “Recent cyber security attacks and their mitigation approaches–an overview”. In International conference on applications and techniques in information security (2016): 54-65.
4. El-Rewini Z., et al. “Cybersecurity challenges in vehicular communications”. Vehicular Communications23 (2020): 100214.‏
5. Handa A., et al. “Machine learning in cybersecurity: A review”. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery9.4 (2019): e1306.‏
6. Kumar V., et al. “An integrated rule based intrusion detection system: analysis on UNSW-NB15 data set and the real time online dataset”. Cluster Computing2 (2020): 1397-1418.‏
7. Amaizu GC., et al. “Investigating Network Intrusion Detection Datasets Using Machine Learning”. In 2020 International Conference on Information and Communication Technology Convergence (ICTC) (2020): 1325-1328.‏
8. Kasongo S M and Sun Y. “Performance analysis of intrusion detection systems using a feature selection method on the UNSW-NB15 dataset”. Journal of Big Data1 (2020): 1-20.‏
9. Tuan T A., et al. “Performance evaluation of Botnet DDoS attack detection using machine learning”. Evolutionary Intelligence (2019): 1-12.‏
10. Shushlevska M., et al. “Anomaly detection with various machine learning classification techniques over UNSW-nb15 dataset” (2022).‏
11. Moustafa N and Slay J. “UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set)”. In 2015 military communications and information systems conference (MilCIS) (2015): 1-6.‏
12. Hancock J T and Khoshgoftaar T M. “Survey on categorical data for neural networks”. Journal of Big Data7.1 (2020): 1-41.‏
13. Pal M. “Random forest classifier for remote sensing classification”. International Journal of Remote Sensing1 (2005): 217-222.‏
14. Farnaaz N and Jabbar M A. “Random forest modeling for network intrusion detection system”. Procedia Computer Science89 (2016): 213-217.‏
15. Idhammad M., et al. “Detection system of HTTP DDoS attacks in a cloud environment based on information theoretic entropy and random forest”. Security and Communication Networks (2018).
16. Kingsford C and Salzberg SL. “What are decision trees?”. Nature Biotechnology9 (2008): 1011-1013.‏
17. Quinlan J R. “Induction of decision trees”. Machine Learning1 (1986) 81-106.‏
18. De Ville B. “Decision trees”. Wiley Interdisciplinary Reviews: Computational Statistics6 (2013): 448-455.‏
19. Kotsiantis SB. “Decision trees: a recent overview”. Artificial Intelligence Review39.4 (2013): 261-283.‏
20. Amor N B., et al. “Naive bayes vs decision trees in intrusion detection systems”. In Proceedings of the 2004 ACM symposium on Applied computing (2004): 420-424.‏
21. Noriega L. “Multilayer perceptron tutorial”. School of Computing. Staffordshire University (2005).‏
22. Tang J., et al. “Extreme learning machine for multilayer perceptron”. IEEE transactions on neural networks and learning systems 27.4 (2015): 809-821.‏
23. Ramchoun H., et al. “Multilayer perceptron: Architecture optimization and training” (2016).
24. Mitchell R and Frank E. “Accelerating the XGBoost algorithm using GPU computing”. Peer Journal of Computer Science3 (2017): e127.‏
25. Pan B. “Application of XGBoost algorithm in hourly PM2. 5 concentration prediction”. In IOP conference series: earth and environmental science 113.1 (2018): 012127.‏
26. Dong W., et al. “XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring”. Automation in Construction114 (2020): 103155.‏
27. Hu W and Hu W. “Network-based intrusion detection using Adaboost algorithm”. In The 2005 IEEE/WIC/ACM International Conference on Web Intelligence (WI'05) (2005): 712-717.‏
28. Jabri S., et al. “Moving vehicle detection using Haar-like, LBP and a machine learning Adaboost algorithm”. In 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS) (2018): 121-124.‏
29. Yuan L and Zhang F. “Ear detection based on improved adaboost algorithm”. In 2009 International Conference on Machine Learning and Cybernetics (2009): 2414-2417.‏
30. Son J., et al. “Tracking-by-segmentation with online gradient boosting decision tree”. In Proceedings of the IEEE international conference on computer vision (2015): 3056-3064.‏
31. Peter S., et al. “Cost efficient gradient boosting”. Advances in Neural Information Processing Systems 30 (2017).
32. Lusa L. “Gradient boosting for high-dimensional prediction of rare events”. Computational Statistics and Data Analysis113 (2017): 19-37.‏
33. Kumar U K., et al. “Prediction of breast cancer using voting classifier technique”. In 2017 IEEE international conference on smart technologies and management for computing, communication, controls, energy and materials (ICSTM) (2017): 108-114.‏
34. El-Kenawy E S M., et al. “Novel feature selection and voting classifier algorithms for COVID-19 classification in CT images”. IEEE Access8 (2020): 179317-179335.‏
35. Khan M A., et al. “Voting classifier-based intrusion detection for iot networks”. In Advances on Smart and Soft Computing (2022): 313-328.
36. Mahabub A. “A robust technique of fake news detection using Ensemble Voting Classifier and comparison with other classifiers”. SN Applied Sciences 2.4 (2020): 1-9.‏
37. Dalianis H. “Evaluation metrics and evaluation”. In Clinical text mining (2018): 45-53.

Citation

Citation: Saif Rawashdeh. “Applying Machine Learning Techniques in Cybersecurity Field".Acta Scientific Computer Sciences 5.11 (2023): 30-39.

Copyright

Copyright: © 2023 Saif Rawashdeh. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.