Review Of LightGBM-Based Machine Learning Techniques for Network Outlier Detection
Keywords:
LightGBM, network outlier detection, machine learning, intrusion detection, anomaly detection, network security, IoT, feature selection, cybersecurity, network traffic classification.Abstract
The rapid growth of computer networks, Internet of Things devices and interconnected digital systems has increased the need for effective techniques to identify abnormal and potentially malicious network traffic. This review examines LightGBM-based machine learning techniques for network outlier detection, focusing on their methodological development, reported performance and applicability across different network environments. The study adopts a secondary research methodology and reviews relevant academic literature published between 2015 and 2024. Particular attention is given to the use of LightGBM with feature selection, data-balancing techniques, hyperparameter optimisation and hybrid machine learning architectures. The reviewed evidence indicates that LightGBM can provide strong detection performance while maintaining comparatively efficient computational requirements, particularly when applied to high-dimensional network datasets. Its application has expanded from conventional intrusion detection datasets to IoT and resource-constrained environments. However, challenges associated with class imbalance, dataset dependency, feature selection, generalisation and real-time deployment remain evident. The review highlights the importance of appropriate preprocessing and evaluation strategies in determining model effectiveness and identifies opportunities for developing more adaptive, scalable and reliable LightGBM-based network outlier detection frameworks.
References
Alharbi, A., Alzahrani, A., & Alghamdi, T. (2023). A new intrusion detection system for secured IoT/IIoT networks based on a LightGBM-based approach. Gazi University Journal of Science, 36(4), 1–15.
Cong, Y.-Q., Guan, T., Cui, J.-F., & Cheng, X.-G. (2022). LGBM: An intrusion detection scheme for resource-constrained end devices in Internet of Things. Security and Communication Networks, 2022, Article 1761655. https://doi.org/10.1155/2022/1761655
Deng, Y. (2024). Design of industrial IoT intrusion security detection system based on LightGBM feature algorithm and multi-layer perception network. Journal of Cyber Security and Mobility, 13(2), 327–348. https://doi.org/10.13052/jcsm2245-1439.1327
Islam, M. K., Hridi, P., Hossain, M. S., & Narman, H. S. (2020). Network anomaly detection using LightGBM: A gradient boosting classifier. In 2020 30th International Telecommunication Networks and Applications Conference (ITNAC) (pp. 1–7). IEEE. https://doi.org/10.1109/ITNAC50341.2020.9315049
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 30 (pp. 3146–3154). Curran Associates.
Khraisat, A., Gondal, I., Vamplew, P., & Kamruzzaman, J. (2019). Survey of intrusion detection systems: Techniques, datasets and challenges. Cybersecurity, 2, Article 20. https://doi.org/10.1186/s42400-019-0038-7
Leevy, J. L., & Khoshgoftaar, T. M. (2020). A survey and analysis of intrusion detection models based on CSE-CIC-IDS2018 Big Data. Journal of Big Data, 7, Article 104. https://doi.org/10.1186/s40537-020-00382-x
Moustafa, N., & Slay, J. (2015). 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) (pp. 1–6). IEEE. https://doi.org/10.1109/MilCIS.2015.7348942
Moustafa, N., & Slay, J. (2015). The significant features of the UNSW-NB15 and KDD99 data sets for network intrusion detection systems. In Proceedings of the 2015 4th International Workshop on Building Analysis Datasets and Gathering Experience Returns for Security (BADGERS) (pp. 25–31). IEEE.
Ring, M., Wunderlich, S., Grüdl, D., Landes, D., & Hotho, A. (2019). A survey of network-based intrusion detection data sets. Computers & Security, 86, 147–167.
Sharafaldin, I., Lashkari, A. H., & Ghorbani, A. A. (2018). Toward generating a new intrusion detection dataset and intrusion traffic characterization. In Proceedings of the 4th International Conference on Information Systems Security and Privacy (pp. 108–116). SCITEPRESS. https://doi.org/10.5220/0006639801080116
Zhang, H., Ge, L., Wang, Z., & colleagues. (2022). A high performance intrusion detection system using LightGBM based on oversampling and undersampling. In Intelligent Computing Theories and Application (pp. 638–652). Springer. https://doi.org/10.1007/978-3-031-13870-6_53
Zhao, G., Wang, Y., & Wang, J. (2023). Intrusion detection model of Internet of Things based on LightGBM. IEICE Transactions on Communications, E106-B(8), 622–634. https://doi.org/10.1587/transcom.2022EBP3169
Downloads
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Engineering Science & Humanities
This work is licensed under a Creative Commons Attribution 4.0 International License.
