Abstract

Intrusion Detection Systems (IDS) are essential components of modern cybersecurity infrastructures because they help identify unauthorized access, malicious activities, and cyber threats within network environments. However, traditional signature-based intrusion detection approaches often struggle to detect sophisticated and emerging attacks due to their reliance on predefined attack patterns. This study presents a machine learning-based intrusion detection framework using the UNSW-NB15 dataset to improve network attack detection accuracy and reliability. Five machine learning classifiers, namely Naive Bayes, Bagging, Random Forest, Multi-Layer Perceptron, and XGBoost, were implemented and comparatively evaluated for binary classification of network traffic into normal and malicious categories. Data preprocessing techniques such as feature scaling, label encoding, and train-test splitting were applied before model training and evaluation. The performance of the classifiers was assessed using accuracy, precision, recall, and F1-score metrics with weighted averaging to address class imbalance challenges within the dataset. Experimental results showed that ensemble learning approaches significantly outperformed individual classifiers. Among the evaluated models, XGBoost achieved the best overall performance with an accuracy of 90.07% and an F1-score of 89.77%, demonstrating strong capability in balancing precision and recall for intrusion detection tasks. The findings of this study indicate that XGBoost provide robust and reliable solutions for modern intrusion detection systems and can effectively improve cybersecurity defenses in contemporary network environments.

References

• Ferrag, M. A., Maglaras, L., Moschoyiannis, S., and Janicke, H. 2020. Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, vol. 50.
• Shone, N., Ngoc, T. N., Phai, V. D., and Shi, Q. 2018. A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 2, no. 1, pp. 41–50.
• Tama B. A., and Lim, S. 2020. Ensemble learning for intrusion detection systems: A systematic mapping study and cross-benchmark evaluation. Computer Science Review, vol. 39.
• Alazzam, H., Sharieh, A., and Sabri, K. E. 2022. A feature selection algorithm for intrusion detection system based on Pigeon Inspired Optimizer. Expert Systems with Applications, vol. 148.
• Vinayakumar, R., Soman, K. P., Poornachandran, P., and Akarsh, S. 2019. Evaluating deep learning approaches to characterize and classify network traffic. Journal of Intelligent & Fuzzy Systems, vol. 36, no. 5, pp. 4775–4785.
• Moustafa N., and Slay, J. 2015. UNSW-NB15: A comprehensive data set for network intrusion detection systems. In Proc. MilCIS, pp. 1–6.
• Breiman, L. 1996. Bagging predictors. Machine Learning, vol. 24, no. 2, pp. 123–140.
• Breiman, L. 2001. Random forests. Machine Learning, vol. 45, no. 1, pp. 5–32.
• Chen T., and Guestrin, C. 2016. XGBoost: A scalable tree boosting system. In Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794.
• Haykin, S. 1999. Neural Networks: A Comprehensive Foundation, 2nd ed. Prentice Hall.
• Lemaître, G., Nogueira, F., and Aridas, C. K. 2017. Imbalanced-learn: A Python toolbox to tackle the curse of imbalanced datasets in machine learning. Journal of Machine Learning Research, vol. 18, no. 17, pp. 1–5.
• Liu, X. Y., Wu, J., and Zhou, Z. H. 2009. Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B, vol. 39, no. 2, pp. 539–550.
• Rish, I. 2001. An empirical study of the Naive Bayes classifier. IJCAI Workshop on Empirical Methods in Artificial Intelligence, pp. 41–46.