Hierarchical Attention-Based Convolutional Neural Network Model for Intrusion Detection

Authors

Keywords:

Intrusion detection, convolutional neural networks, real data, cybersecurity, deep learning

Abstract

The increasing scale and complexity of internet-connected systems demand robust intrusion detection under realistic traffic conditions. This study presents H.A.L.C.CO.N (Hierarchical Attention-based Loss Equalization with CatBoost-enhanced Convolutional Neural Network), a multiclass intrusion detection model evaluated on the real-world LITNET-2020 dataset. The model integrates convolutional feature extraction, hierarchical attention, CatBoost-based encoding for high-cardinality categorical features, and Equalization Loss V2 (EQLv2) to address severe class imbalance. Experimental results show strong performance, achieving a detection rate of 99.997%, an F1-score of 99.997%, an accuracy of 99.996%, and a false positive rate of 0.0135%. These findings indicate that H.A.L.C.CO.N is an effective and practical solution for real-world multiclass intrusion detection.

Downloads

Download data is not yet available.

Author Biographies

Rodolfo Martínez Cadena, Universida Juárez Autónoma de Tabasco

Rodolfo Martinez Cadena holds a Master’s Degree in Computational Sciences from Universidad Juárez Autónoma de Tabasco and a Bachelor’s Degree in Electronics and Communications Engineering from Universidad Olmeca in 2003. His professional achievements include leading AI transformations at SEIENER and managing large-scale projects, such as the Ixachi 3D seismic survey. He is also deeply interested in emerging technologies such as brain-computer interfaces, augmented and virtual reality, and Internet of Things (IoT), as well as the application of AI to real-time biomechanical analysis and geophysical exploration. In addition to his technical work, Martinez has contributed to community and entrepreneurial projects. He combines academic excellence, professional expertise, and a passion for using technology to solve real-world problems and drive social impact.

José Adán Hernández-Nolasco, Universidad Juárez Autónoma de Tabasco

José Hernández received the bachelor’s degree in electronic and communications engineering from the Autonomous University of Nuevo León, in 1996, the M.Sc. degree in electronic engineering (telecommunications) from the Monterrey Institute of Technology and Higher Education, in 2003, and the Ph.D. degree in optics from the National Institute for Astrophysics, Optics and Electronics, in 2012. He has been a Research Professor with the Universidad Juárez Autónoma de Tabasco, for 25 years. He has authored or coauthored over 25 publications in the areas of ambient intelligence and AI applications, and over 30 participations in conferences. His research interests include artificial intelligence, fuzzy logic, IoT, and optics

Noel Zacarias-Morales, Universidad Juárez Autónoma de Tabasco

Noel Zacarias Morales is a graduate of the PhD in Computer Science at the Academic Division of Information Sciences and Technologies at the Universidad Juárez Autónoma de Tabasco. He obtained his Master’s degree in Information Technology Management at the Universidad Juárez Autónoma de Tabasco in 2019. His research interests are the development of models based on deep learning (artificial neural networks) applied to signal analysis and processing for prediction and classification

References

L. Wenchao, Y. Ping, W. Yue, P. Li, and L. Jianhua, “A new intrusion detection system based on knn classification algorithm in wireless sensor network,” Journal of Electrical and Computer Engineering, vol. 78, 2014. [Online]. Available: https://doi.org/10.1155/2014/240217

S. Wagh, V. K. Pachghare, and S. R. Kolhe, “Survey on intrusion detection system using machine learning techniques,” International Journal of Computer Applications, vol. 78, 2013. [Online]. Available: https://doi.org/10.5120/13608-1412

R. Vinayakumar, M. Alazab, K. P. Soman, P. Poornachandran, A. Al-Nemrat, and S. Venkatraman, “Deep learning approach for intelligent intrusion detection system,” IEEE Access, vol. 7, pp. 41525–41550, 2019. [Online]. Available: https://doi.org/10.1109/ACCESS.2019.2895334

J. Yan, D. Jin, C. W. Lee, and P. Liu, “A comparative study of off-line deep learning based network intrusion detection,” 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN), pp. 299–304, 2018. [Online]. Available: https://doi.org/10.1109/ICUFN.2018.8436774

K. Ren, S. Yuan, C. Zhang, Y. Shi, and Z. Huang, “CANET: A hierarchical CNN-attention model for network intrusion detection,” Computer Communications, vol. 205, pp. 170–181, 2023. [Online]. Available: https://doi.org/10.1016/j.comcom.2023.04.018

J. Tan, X. Lu, G. Zhang, C. Yin, and Q. Li, “Equalization loss v2: A new gradient balance approach for long-tailed object detection,” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1685–1694, 2021. [Online]. Available: https://doi.org/10.1109/CVPR46437.2021.00173

N. Moustafa and J. Slay, “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), 2015, pp. 1–6. [Online]. Available: https://doi.org/10.1109/MilCIS.2015.7348942

R. Damasevicius, A. Venckauskas, S. Grigaliunas, J. Toldinas, N. Morkevicius, T. Aleliunas, and P. Smuikys, “LITNET-2020: An annotated real-world network flow dataset for network intrusion detection,” Electronics, vol. 9, no. 5, p. 800, 2020. [Online]. Available: https://doi.org/10.3390/electronics9050800

A. Khraisat, I. Gondal, P. Vamplew, and J. Kamruzzaman, “Survey of intrusion detection systems: techniques, datasets and challenges,” Cybersecurity, vol. 2, no. 1, p. 20, Jul. 2019. [Online]. Available: https://doi.org/10.1186/s42400-019-0038-7

I. Ahmad, M. Basheri, M. J. Iqbal, and A. Rahim, “Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection,” IEEE Access, vol. 6, pp. 33789–33795, 2018. [Online]. Available: https://doi.org/10.1109/ACCESS.2018.2841987

W. Hu, J. Gao, Y. Wang, O. Wu, and S. Maybank, “Online Adaboost-based parameterized methods for dynamic distributed network intrusion detection,” IEEE Transactions on Cybernetics, vol. 44, no. 1, pp. 66–82, 2014. [Online]. Available: https://doi.org/10.1109/TCYB.2013.2247592

W. Wang, Y. Sheng, J. Wang, X. Zeng, X. Ye, Y. Huang, and M. Zhu, “HAST-IDS: Learning hierarchical spatial-temporal features using deep neural networks to improve intrusion detection,” IEEE Access, vol. 6, pp. 1792–1806, 2018. [Online]. Available: https://doi.org/10.1109/ACCESS.2017.2780250

J. Sinha and M. Manollas, “Efficient deep CNN-BiLSTM model for network intrusion detection,” in Proceedings of the 2020 3rd International Conference on Artificial Intelligence and Pattern Recognition, 2020, pp. 223–231. [Online]. Available: https://doi.org/10.1145/3430199.3430224

P. Wu, H. Guo, and N. Moustafa, “Pelican: A deep residual network for network intrusion detection,” in 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2020, pp. 55–62. [Online]. Available: https://doi.org/10.1109/DSN-W50199.2020.00018

S. Chaudhari, G. Polatkan, R. Ramanath, and V. Mithal, “A comprehensive review of attention mechanisms in deep learning,” arXiv preprint arXiv:1904.02874, 2020. [Online]. Available: https://doi.org/10.48550/arXiv.1904.02874

J. Kim, J. Kim, and H. K. Kim, “Attention-based recurrent neural network for network intrusion detection,” 2018 International Conference on Big Data and Smart Computing (BigComp), pp. 313–316, 2018. [Online]. Available: https://doi.org/10.1109/BIGCOMP.2018.00055

R. Sommer and V. Paxson, “Outside the closed world: On using machine learning for network intrusion detection,” 2010 IEEE Symposium on Security and Privacy, pp. 305–316, 2010. [Online]. Available: https://doi.org/10.1109/SP.2010.25

I. Sharafaldin, A. H. Lashkari, S. Hakak, and A. A. Ghorbani, “Developing realistic distributed denial of service (DDoS) attack dataset and taxonomy,” in 2019 International Carnahan Conference on Security Technology (ICCST), 2019, pp. 1–8. [Online]. Available: https://doi.org/10.1109/CCST.2019.8888419

L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: unbiased boosting with categorical features,” Advances in Neural Information Processing Systems, vol. 31, 2018. [Online]. Available: https://doi.org/10.48550/arXiv.1810.11363

P. Wu and H. Guo, “LuNet: A deep neural network for network intrusion detection,” in 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 2019, pp. 617–624. [Online]. Available: https://doi.org/10.1109/SSCI44817.2019.9003126

Downloads

Published

2026-06-12

How to Cite

Martínez Cadena, R., Hernández-Nolasco, J. A. ., & Zacarias-Morales, N. (2026). Hierarchical Attention-Based Convolutional Neural Network Model for Intrusion Detection. IEEE Latin America Transactions, 24(8), 776–784. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/10406

Issue

Vol. 24 No. 8 (2026): Ordinary Issue

Section

Computing