Hybrid Adaptive Ensemble with Dynamic Feature Selection for DDoS Attack Detection

Musaev Mukhammadjon, Rakhmatov Furkat
Bulletin of TUIT: Management and Communication Technologies
№ 1(10)2025 DOI:10.61663/251tuitmct10
Open article file

Abstract

Distributed Denial of Service attacks continue to represent a significant challenge for intrusion detection systems due to their scale, diversity, and evolving nature. This paper introduces a novel hybrid adaptive ensemble with dynamic feature selection, which integrates three distinct components: Light Gradient Boosting Machine, one-dimensional convolutional neural network, and Isolation Forest. The proposed ensemble employs Shapley Additive Explanations to perform adaptive feature selection, which enhances classification performance while reducing computational complexity. Experimental evaluation using the CICIDS two thousand seventeen dataset demonstrates that the proposed model achieves an accuracy of ninety-nine point nine five percent, an F one score of ninety-nine point nine five percent, and a recall of ninety-nine point nine two percent. Comparative analysis with existing methods confirms that the proposed approach offers superior effectiveness, robustness, and scalability in detecting distributed denial of service attacks.

References

[1] Elubeyd, H.; Yiltas-Kaplan, D. Hybrid Deep Learning Approach for Automatic DoS/DDoS Attacks Detection in Software-Defined Networks. Appl. Sci. 2023, 13, 3828. https://doi.org/10.3390/app13063828
[2] Mourouzis, Theodosis & Avgousti, Andreas. (2021). Intrusion Detection with Machine Learning Using Open-Sourced Datasets. 10.48550/arXiv.2107.12621.
[3] Verizon: 2024 Data Breach Investigations Report. https://www.verizon.com/business/resources/Te3/reports/2024-dbir-data-breach-investigations-report.pdf
[4] Teeb Hussein Hadi. Deep Learning-based DDoS Detection in Network Traffic Data. International journal of electrical and computer engineering systems, Volume 15, Number 5, 2024, pp. 407-414. https://www.researchgate.net/figure/The-number-of-instances-in-each-class-of-the-NSL-KDD-dataset_tbl1_380593045
[5] Woo-Seong KIM, Hyun-Jung KIM. Bi-LSTM-XGBoost ensemble-based intrusion detection system: Addressing data imbalance and enhancing minority class performance. Edelweiss Applied Science and Technology, Vol. 9 No. 3, pp. 2993-2999, 2025. https://doi.org/10.55214/25768484.v9i3.5899
[6] Assis, M.V.; Carvalho, L.F.; Lloret, J.; Proença, M.L., Jr. A GRU deep learning system against attacks in software defined networks. J. Netw. Comput. Appl. 2021, 177, 102942.
[Google Scholar]
[CrossRef]
[7] CICIDS2017: https://www.unb.ca/cic/datasets/ids-2017.html.
[8] Buczak, A. L., & Guven, E. A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection. IEEE Communications Surveys & Tutorials, vol. 18, no. 2, pp. 1153-1176, 2016.
[9] Goryunov M.N., Matskevich A.G., Rybolovlev D.A. Synthesis of a Machine Learning Model for Detecting Computer Attacks Based on the CICIDS2017 Dataset. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2020;32(5):81-94. (In Russ.) https://doi.org/10.15514/ISPRAS-2020-32(5)-6
[10] Elsaid, S.A., Binbusayyis, A. An optimized isolation forest based intrusion detection system for heterogeneous and streaming data in the industrial Internet of Things (IIoT) networks. Discov Appl Sci 6, 483 (2024). https://doi.org/10.1007/s42452-024-06165-w
[11] Lundberg, S. M., & Lee, S. I. A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, pp. 4765-4774, 2017.
[12] Ke, G., et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Advances in Neural Information Processing Systems, pp. 3146-3154, 2017.
[13] LeCun, Y., et al. Deep Learning. Nature, vol. 521, no. 7553, pp. 436-444, 2015.
[14] Liu, F. T., et al. Isolation Forest. IEEE International Conference on Data Mining, pp. 413-422, 2008.
[15] Moustafa, N., & Slay, J. UNSW-NB15: A Comprehensive Data Set for Network Intrusion Detection Systems. Military Communications and Information Systems Conference, 2015.
[16] Koroniotis, N., et al. Towards the Development of Realistic Botnet Dataset in the Internet of Things. Future Generation Computer Systems, vol. 92, pp. 888-901, 2019.
[17] Kreps, J., et al. Kafka: A Distributed Messaging System for Log Processing. NetDB Workshop, 2011.
[18] Howard, A. G., et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861, 2017.
[19] Karimov, N., Rakhmatov, F., and Xolmuminov, O. Detection of HTTP Flood attacks based on machine learning algorithms. Chemical Technology, Control and Management: Vol. 2025: Iss. 2, Article 10, 2025. DOI: https://doi.org/10.59048/2181-1105.1663