Robust Network Intrusion Detection Using Deep Stacking Ensembles and Hybrid Feature Selection
DOI:
https://doi.org/10.58564/IJCCN.2.1.2026.14Keywords:
Intrusion Detection System, NSL-KDD, Feature Selection, SMOTE, Stacking Ensemble, Neural Network, Network Security, CybersecurityAbstract
In the contemporary networked systems, network security has emerged to be a critical issue. Intrusion Detection Systems (IDS) are imperative defense systems that can be used to detect malicious network traffic. The study provides a new IDS model, which combines various machine learning models and deep learning architectures to generate better detection accuracy on the NSL-KDD benchmark data. The researchers make four main contributions: (1) a hybrid approach to feature selection which involves Information Gain and correlation-based redundancy elimination, (2) Synthetic Minority Oversampling Technique (SMOTE) to overcome the class imbalance, (3) a stacking ensemble classifier, and (4) a Deep Neural Network (DNN) with Batch Normalization, LeakyReLU activation, and Dropout regularization. Through experiment, it has been shown that the proposed stacking ensemble has an accuracy of 99.80 and an F1-score of 0.998 on binary classification, and 99.53 and five attack categories on multi-class classification. The proposed strategy is much better than individual baseline classifiers and has strong detection ability of minority attack classes such as R2L and U2R attacks.
References
[1] Denning, D.E. (1987). An intrusion-detection model. IEEE Transactions on Software Engineering, SE-13(2), 222-232.
[2] Tavallaee, M., Bagheri, E., Lu, W., & Ghorbani, A.A. (2009). A detailed analysis of the KDD CUP 99 data set. In Proceedings of the Second IEEE Symposium on Computational Intelligence for Security and Defence Applications.
[3] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
[4] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
[5] Chawla, N.V., Bowyer, K.W., Hall, L.O., & Kegelmeyer, W.P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321-357.
[6] Negandhi, P., Trivedi, Y., & Mangrulkar, R. (2019). Intrusion detection system using random forest on the NSL-KDD dataset. In Emerging Research in Computing, Information, Communication and Applications, Springer.
[7] Wolpert, D.H. (1992). Stacked generalization. Neural Networks, 5(2), 241-259.
[8] Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning.
[9] Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929-1958.
[10] Ingre, B., & Yadav, A. (2015). Performance analysis of NSL-KDD dataset using ANN. In International Conference on Signal Processing and Communication Engineering Systems.
[11] Wahba, Y., ElSalamouny, E., & ElTawee, G. (2015). Improving the performance of multi-class intrusion detection systems using feature reduction. IJCSI International Journal of Computer Science Issues, 12(3).
[12] Chae, H., Jo, B., Choi, S.H., & Park, T. (2013). Feature selection for intrusion detection using NSL-KDD. Recent Advances in Computer Science, 184-187.
[13] Li, X., Chen, W., Zhang, Q., & Wu, L. (2022). Intrusion detection system combined enhanced random forest with SMOTE algorithm. EURASIP Journal on Advances in Signal Processing.
[14] 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.
[15] Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
[16] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In Proceedings of the IEEE International Conference on Computer Vision.
[17] Scikit-learn: Machine Learning in Python, Pedregosa et al., JMLR 12, pp. 2825-2830, 2011.
[18] Abadi, M., et al. (2016). TensorFlow: A system for large-scale machine learning. In 12th USENIX Symposium on Operating Systems Design and Implementation.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Shahad Aman Ibrahim
This work is licensed under a Creative Commons Attribution 4.0 International License.
