Robust Network Anomaly Detection through Meta-Ensemble Learning: Comparative Evaluation of Eight Classifiers

doi:10.23940/ijpe.26.03.p1.119127

Abstract

Abstract:

Effective detection of network anomalies is crucial when it comes to security of computer networks, but traditional methods tend to fail when used to address a wide range of traffic and dynamically changing conditions. This paper provides a systematic review of eight ensemble algorithms, including Random Forest, Extra Trees, Bagging, AdaBoost, Gradient Boosting, HistGradientBoosting, Stacking and Voting, on a dataset of 4,998 samples where 35 features were statistics of network traffic. The data underwent preprocessing based on cleaning, normalization and encoding, and we evaluated the models based on stratified 10-fold cross-validation which used accuracy, precision, recall, F1-score and AUC. Our findings reveal that Stacking with a meta-ensemble produced the best results of 98.90 percent and Voting closely followed with 98.85 percent. Random Forest and Extra Trees also showed strong results of more than 98 percent, whereas the weakest result of 78 percent was obtained in Gradient Boosting, which is sensitive to the configuration of the data. These results offer solid empirical support that ensemble architectures, specifically stacking and voting, offer highly precise, scalable, and practical solutions to state of the art intrusion detection systems.

Key words: network security, anomaly detection, ensemble learning, machine learning applications, intrusion detection systems, SNMP-MIB dataset

Ukamaka Okonkwo Ngozi, Tochukwu Ikwuazom Callistus, Amina Onyeabor Grace, Ada Ukaigwe Jane and Okeahialam Temple. Robust Network Anomaly Detection through Meta-Ensemble Learning: Comparative Evaluation of Eight Classifiers [J]. Int J Performability Eng, 2026, 22(3): 119-127.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References 24

[1]	Hisham, S. , Makhtar, M. , and Aziz, A.A. , 2022. Combining multiple classifiers using ensemble method for anomaly detection in blockchain networks: A comprehensive review. International Journal of Advanced Computer Science and Applications, 13( 8).
[2]	Farooq, M. , and Khan, M.H. , 2022. Signature-based intrusion detection system in wireless 6G IoT networks. Journal on Internet of Things, 4( 3).
[3]	Dutta, V. , Choraś, M. , Pawlicki, M. , and Kozik, R. , 2020. A deep learning ensemble for network anomaly and cyber-attack detection. Sensors, 20( 16), 4583.
[4]	Shafieian, S. , and Zulkernine, M. , 2023. Multi-layer stacking ensemble learners for low footprint network intrusion detection. Complex & Intelligent Systems, 9( 4), pp. 3787- 3799.
[5]	Cosovic, M. , and Junuz, E. , 2019. Bgp anomaly prediction using ensemble learning. International Journal of Machine Learning and Computing, 9( 4).
[6]	Chen, C. , Wang, G. , Yang, B. , Yang, L. , and Ye, X. , 2022. Build intrusion detection model based on CNN and ensemble learning. In International Conference on Signal Processing and Communication Security (ICSPCS 2022) , 12455, pp. 145- 150.
[7]	Thaseen, I.S. , Chitturi, A.K. , Al‐Turjman, F. , Shankar, A. , Ghalib, M.R. , and Abhishek, K. , 2022. An intelligent ensemble of long‐short‐term memory with genetic algorithm for network anomaly identification. Transactions on Emerging Telecommunications Technologies, 33( 10), e4149.
[8]	Han, X. , Chen, X. , and Liu, L.P. , 2021. Gan ensemble for anomaly detection. In Proceedings of the AAAI Conference on Artificial Intelligence , 35( 5), pp. 4090- 4097.
[9]	Wu, Y. , Lee, W.W. , Xu, Z. , and Ni, M. , 2020. Large-scale and robust intrusion detection model combining improved deep belief network with feature-weighted SVM. IEEE Access, 8, pp. 98600- 98611.
[10]	Jadidi, Z. , Foo, E. , Hussain, M. , and Fidge, C. , 2022. Automated detection-in-depth in industrial control systems. the International Journal of Advanced Manufacturing Technology, 118( 7), pp. 2467- 2479.
[11]	Xu, X. , and Zheng, X. , 2021. Hybrid model for network anomaly detection with gradient boosting decision trees and tabtransformer. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8538- 8542.
[12]	Wang, X. , 2022. A collaborative detection method of wireless mobile network intrusion based on cloud computing. Wireless Communications and Mobile Computing, 2022( 1), 1499736.
[13]	Tufan, E. , Tezcan, C. , and Acartürk, C. , 2021. Anomaly-based intrusion detection by machine learning: A case study on probing attacks to an institutional network. IEEE Access, 9, pp. 50078- 50092.
[14]	Li, Y. , Wei, S. , Liu, X. , and Zhang, Z. , 2021. A novel robust fuzzy rough set model for feature selection. Complexity, 2021( 1), 6685396.
[15]	Thapa, N. , Liu, Z. , Kc, D.B. , Gokaraju, B. , and Roy, K. , 2020. Comparison of machine learning and deep learning models for network intrusion detection systems. Future Internet, 12( 10), 167.
[16]	Nanda, M.K. , and Patra, M.R. , 2020. Intrusion detection and classification using decision tree-based feature selection classifiers. In Intelligent and Cloud Computing: Proceedings of ICICC 2019, Volume 2, pp. 157- 170.
[17]	Das, S. , Islam, M.R. , Jayakodi, N.K. , and Doppa, J.R. , 2024. Effectiveness of tree-based ensembles for anomaly discovery: insights, batch and streaming active learning. Journal of Artificial Intelligence Research, 80, pp. 127- 170.
[18]	Mu, H. , Aljeri, N. , and Boukerche, A. , 2024. Spatio-temporal feature engineering for deep learning models in traffic flow forecasting. IEEE Access, 12, pp. 76555- 76578.
[19]	Singh, V. , Sahana, S.K. , and Bhattacharjee, V. , 2025. A novel CNN-GRU-LSTM based deep learning model for accurate traffic prediction. Discover Computing, 28( 1), 38.
[20]	Zhang, J. , Sha, J. , Zhang, C. , and Zhang, Y. , 2025. A CNN-LSTM-GRU hybrid model for spatiotemporal highway traffic flow prediction. Systems, 13( 9), 765.
[21]	Gupta, A. , Phulre, A.K. , Patel, A. , and Rahman, R.U. , 2024. Hybrid ensemble learning with explainable ai for anomaly detection in network traffic. In 2024 First International Conference on Innovations in Communications, Electrical and Computer Engineering (ICICEC) , pp. 1- 8.
[22]	Padmalatha, E. , Reddy, R.R. , Devi, G.M. , and Sri, R.L.S. , 2025. Network anomaly detection using similarity-aware ensemble learning. In 2025 6th International Conference on Mobile Computing and Sustainable Informatics (ICMCSI) , pp. 678- 685.
[23]	Tian, Y. , Yin, S. , Liang, S. , and Geng, H. , 2025. Network anomaly traffic detection method based on ensemble learning and feature fusion. In International Conference on Computer Application and Information Security (ICCAIS 2024) , 13562, pp. 1164- 1174.
[24]	Yuan, X. , Zhou, N. , Yu, S. , Huang, H. , Chen, Z. , and Xia, F. , 2021. Higher-order structure based anomaly detection on attributed networks. In 2021 IEEE International Conference on Big Data (Big Data), pp. 2691- 2700.