SDAE-GAN for Handling Class Imbalance in The UNSW-NB15 Dataset
DOI:
https://doi.org/10.32832/astonjadro.v15i4.22980Keywords:
intrusion detection system, class imbalance, data augmentation, stacked denoising autoencoder, generative adversarial network, UNSW-NB15, SVM.Abstract
Dataset for Intrusion Detection Systems (IDS) are often 'imbalanced', where normal data conditions are too abundant while attack data is very scarce. This condition makes machine learning performance in detecting attacks poor, especially for attacks that are indeed rare. Previous research addressed this issue by applying Stacked Denoising Autoencoder (SDAE), which can reduce the dimensions of features in large datasets. In this study, researchers explored the potential use of SDAE but combined it with Generative Adversarial Networks (GAN). SDAE was adopted not for dimension reduction, but with a different approach to augmentation or multiplying minority attack class data. With the SDAE-GAN hybrid model, the researchers proposed an architecture using an SDAE-based generator trained in a GAN framework to generate realistic synthetic data for each minority attack class in the UNSW-NB15 dataset. This process balanced the data distribution before training the classification model. The researchers then tested the model using Support Vector Machine (SVM) on the balanced data. The results were very significant, with the SVM model achieving 97% accuracy, an F1-Score of 98.44%, and, most importantly, a near-perfect recall value of 99.67% in detecting attack classes. This shows that the SDAE-GAN hybrid augmentation method can overcome the imbalance problem and drastically improve the IDS's ability to detect attacks from minority classes.
References
[1] A. D. Vibhute, M. Khan, C. H. Patil, S. V Gaikwad, A. V Mane, and K. K. Patel, “Network anomaly detection and performance evaluation of Convolutional Neural Networks on UNSW-NB15 dataset,” Procedia Comput. Sci., vol. 235, pp. 2227–2236, 2024.
[2] F. M. Anis, M. AlAbdullatif, S. Aljbli, and M. Hammoudeh, “A Survey on the Applications of Deep Learning in Network Intrusion Detection Systems to Enhance Network Security,” IEEE Access, 2025.
[3] M. Umer, M. Tahir, M. Sardaraz, M. Sharif, H. Elmannai, and A. D. Algarni, “Network intrusion detection model using wrapper based feature selection and multi head attention transformers,” Sci. Rep., vol. 15, no. 1, p. 28718, 2025.
[4] S. Saiharish and D. Kumar, “Network intrusion detection through stacked machine learning models on UNSW-NB15 dataset,” in 2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), IEEE, 2024, pp. 1–7.
[5] J. J. Davis and A. J. Clark, “Data preprocessing for anomaly based network intrusion detection: A review,” Comput. Secur., vol. 30, no. 6–7, pp. 353–375, 2011.
[6] E. M. Timofte et al., “Federated learning for cybersecurity: A privacy-preserving approach,” Applied Sciences, vol. 15, no. 12, p. 6878, 2025.
[7] M. A. Umar, C. Zhanfang, and Y. Liu, “Network intrusion detection using wrapper-based decision tree for feature selection,” in Proceedings of the 2020 International Conference on Internet Computing for Science and Engineering, 2020, pp. 5–13.
[8] S. Debnath, “AI-driven cybersecurity for renewable energy systems: Detecting anomalies with energy-integrated defense data,” Int. J. Appl. Math. (Sofia)., vol. 38, no. 5s, pp. 1002–1032, 2025.
[9] W. Lim, K. S. C. Yong, B. T. Lau, and C. C. L. Tan, “Future of generative adversarial networks (GAN) for anomaly detection in network security: A review,” Comput. Secur., vol. 139, p. 103733, 2024.
[10] M. Y. Jo and H. J. Kim, “A Comparative Study of Lightweight, Sparse Autoencoder-Based Classifiers for Edge Network Devices: An Efficiency Analysis of Feed-Forward and Deep Neural Networks,” Sensors, vol. 25, no. 20, p. 6439, 2025.
[11] Q. Fu and H. Wang, “A novel deep learning system with data augmentation for machine fault diagnosis from vibration signals,” Applied Sciences, vol. 10, no. 17, p. 5765, 2020.
[12] S. M. Kasongo and Y. Sun, “Performance analysis of intrusion detection systems using a feature selection method on the UNSW-NB15 dataset,” J. Big Data, vol. 7, no. 1, p. 105, 2020.
[13] H. Wang, Z. Cao, and B. Hong, “A network intrusion detection system based on convolutional neural network,” Journal of Intelligent & Fuzzy Systems, vol. 38, no. 6, pp. 7623–7637, 2020.
[14] S. More, M. Idrissi, H. Mahmoud, and A. T. Asyhari, “Enhanced intrusion detection systems performance with UNSW-NB15 data analysis,” Algorithms, vol. 17, no. 2, p. 64, 2024.
[15] M. Sohail, M. Hamad, and A. Saeed, “NETWORK INTRUSION DETECTION USING THE UNSW-NB15 DATASET AND THE CONDITIONAL GANAUGMENTED CNN,” in Cryptography and Information Security Trends 2025, Academy & Industry Research Collaboration, Sep. 2025, pp. 97–109. doi: 10.5121/csit.2025.151707.
[16] G. Zhang, X. Wang, R. Li, Y. Song, J. He, and J. Lai, “Network intrusion detection based on conditional Wasserstein generative adversarial network and cost-sensitive stacked autoencoder,” IEEE access, vol. 8, pp. 190431–190447, 2020.
[17] L. Thomas, B. Iv, and A. Vakanski, “A Comparative Analysis of Machine Learning and Deep Learning Approaches for Network Intrusion Detection,” 2025.
[18] M. Lopez-Martin, A. Sanchez-Esguevillas, J. I. Arribas, and B. Carro, “Network intrusion detection based on extended RBF neural network with offline reinforcement learning,” IEEE Access, vol. 9, pp. 153153–153170, 2021.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 ASTONJADRO
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Paper submitted to ASTONJADRO is the sole property of the Astonjadro Journal. Unless the author withdraws the paper because he does not want to be published in this journal. The publication rights are in the journal Astonjadro.ASTONJADRO
LICENSE
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at http://ejournal.uika-bogor.ac.id/index.php/ASTONJADRO
