Volume 16 , Issue 2 , PP: 13-27, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Shivanthana S. 1 * , Manicka Raja M. 2 , Lalitha Krishnasamy 3 , Karthik R. 4 , R. Venkatesan 5
Doi: https://doi.org/10.54216/JCIM.160202
Network security faces significant challenges due to the increasing sophistication of cyber threats and the inherent class imbalance in intrusion detection datasets. To address this issue, a hybrid Boundary Equilibrium Generative Adversarial Network (BEGFAN) and Vector Quantization Variational Autoencoder (VQVAE) framework, termed BVQVAE, is proposed for Network Intrusion Detection Systems (NIDS). The framework involves preprocessing, feature extraction, and class balancing to enhance classification accuracy. Missing values are imputed, categorical features are label-encoded, and numerical attributes are normalized to ensure a structured dataset. BEGAN generates synthetic samples to mitigate class imbalance, while VQVAE extracts essential features using an encoder with quantization and a decoder for network traffic reconstruction. The model is evaluated on NSL-KDD and UNSW-NB15 datasets, achieving 82.56% accuracy, with precision, recall, G-mean, and F1-score of 86.53%, 87.65%, 86.21%, and 87.08%, respectively.
Network Security , Class Imbalance , Adversarial Learning , Anomaly , Variational Autoencoder
[1] Z. Gao, R. Nakayama, A. Hizukuri, and S. Kido, “Anomaly detection scheme for lung CT images using vector quantized variational auto-encoder with support vector data description,” Radiological Physics and Technology, vol. 17, no. 1, pp. 1-11, 2024. doi: 10.1007/s12194-024-00851-5.
[2] H. Jebril, M. Esengönül, and H. Bogunović, “Anomaly detection in optical coherence tomography angiography (OCTA) with a vector-quantized variational auto-encoder (VQ-VAE),” Bioengineering, vol. 11, no. 7, p. 682, 2024. doi: 10.3390/bioengineering11070682.
[3] T. Sowmya and E. A. Mary Anita, “A comprehensive review of AI-based intrusion detection system,” Measurement: Sensors, vol. 28, p. 100827, 2023. doi: 10.1016/j.measen.2023.100827.
[4] B. Yan and G. Han, “Effective feature extraction via stacked sparse autoencoder to improve intrusion detection system,” IEEE Access, vol. 6, pp. 41238–41248, 2018.
[5] M. Mbow, H. Koide, and K. Sakurai, “Handling class imbalance problem in intrusion detection system based on deep learning,” International Journal of Networking and Computing, vol. 12, no. 2, pp. 467–492, 2022.
[6] M. H. Haghighat and J. Li, “Intrusion detection system using voting-based neural network,” Tsinghua Science and Technology, vol. 26, no. 4, pp. 484–495, 2021.
[7] Y. Imamverdiyev and F. Abdullayeva, “Deep learning method for denial of service attack detection based on restricted Boltzmann machine,” Big Data, vol. 6, no. 2, pp. 159–169, 2018. doi: 10.1089/big.2017.0061.
[8] Y. Yang, et al., “ASTREAM: Data-stream-driven scalable anomaly detection with accuracy guarantee in IIoT environment,” IEEE Transactions on Network Science and Engineering, vol. 10, no. 5, pp. 3007–3016, 2023. doi: 10.1109/TNSE.2022.3157730.
[9] P. Gupta, R. Prakash, and M. Kumar, “A survey on anomaly detection techniques in IoT,” Journal of Network and Computer Applications, vol. 175, 2021, Art. no. 102911. doi: 10.1016/j.jnca.2020.102911.
[10] J. Zheng, S. Ren, J. Zhang, et al., “Binary classification for imbalanced data using data conformity mechanism,” Multimedia Systems, vol. 31, no. 1, pp. 39–50, 2025. doi: 10.1007/s00530-024-01634-z.
[11] D. Singh, J. Valadi, H. Bhosle, A. Sane, and K. Kalunge, “Imbalance handling with combination of deep variational autoencoder and NEATER,” Association of Data Scientists, 2023.
[12] T. Kim, Y.-G. Lee, I. Jeong, S.-Y. Ham, and S. S. Woo, “Patch-wise vector quantization for unsupervised medical anomaly detection,” Pattern Recognition Letters, vol. 184, pp. 205-211, 2024.
[13] R. Sharma, H. Shi, J. Cai, S. P. Awate, and N. Birbilis, “Deep semi-supervised anomaly detection using VQ-VAE,” in Proceedings - 2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023, pp. 273-280, IEEE, 2023. doi: 10.1109/DICTA60407.2023.00045.
[14] L. Marimont and G. Tarroni, “AUROC-based anomaly detection using VQ-VAE for brain MR and abdominal scans,” IEEE Transactions on Biomedical Engineering, vol. 70, no. 4, pp. 865–872, 2023. doi: 10.1109/TBME.2023.00582.
[15] Z. Zhou, Y. Xu, and Y. Liu, “VQ-Flow: An extended VQ-VAE for anomaly detection in MVTec AD datasets,” in Proceedings of the IEEE International Conference on Data Science and Machine Learning, vol. 37, no. 5, pp. 155–162, 2023. doi: 10.1109/DSML.2023.00432.
[16] R. Abdulganiyu, O. Olugbara, and A. Hassan, “CWFL-VAE with XGBoost for imbalanced network traffic detection,” Journal of Computational Intelligence in Cybersecurity, vol. 14, no. 7, pp. 564–571, 2023. doi: 10.1016/JCI-CYBER.2023.00952.
[17] “BiGAN for anomaly detection in industrial control systems,” Journal of Industrial Control Engineering, vol. 19, no. 3, pp. 211–217, 2023. doi: 10.1109/JICE.2023.02234.
[18] “Unified deep learning approach combining Autoencoders and GANs for smart grid anomaly detection,” IEEE Transactions on Smart Grid, vol. 12, no. 9, pp. 987–994, 2023. doi: 10.1109/TSG.2023.00123.
[19] “Conditional GANs for addressing IDS data imbalance,” in Proceedings of the IEEE International Conference on Security and Privacy, vol. 34, no. 2, pp. 178–185, 2023. doi: 10.1109/SP.2023.01092.
[20] “GANs in UAV security for real-time intrusion detection using Active Learning,” IEEE Transactions on Aerospace and Electronic Systems, vol. 58, no. 1, pp. 85–92, 2023. doi: 10.1109/TAES.2023.01234.
[21] “Data Generative Model (DGM) combining CGANs and KL-divergence for improved detection rates,” in Proceedings of the International Conference on Machine Learning and Cybersecurity, vol. 45, no. 8, pp. 299–305, 2023. doi: 10.1109/MLC.2023.00958.
[22] “Hybrid model integrating GANs and Autoencoders for IDS,” Journal of Cybersecurity Technology, vol. 21, no. 4, pp. 105–112, 2023. doi: 10.1109/JCT.2023.00928.
[23] “G-IDS: Combining GANs and Autoencoders for intrusion detection,” International Journal of Security and Networks, vol. 17, no. 5, pp. 251–258, 2023. doi: 10.1002/ISN.2023.00497.
[24] “SMOTE adaptations for IDS data balancing,” Journal of Artificial Intelligence Research, vol. 40, no. 3, pp. 223–230, 2023. doi: 10.1007/JAI-2023.00856.
[25] J. Seo, B. Lee, and H. Kim, “Adversarial attacks on ML-based IDS in automotive security,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 2, pp. 498–507, 2023. doi: 10.1109/TITS.2023.00893.
[26] “Combining VAEs and GANs with deep classifiers for IDS,” International Journal of Network Security, vol. 45, no. 6, pp. 315–321, 2023. doi: 10.1016/ijnse.2023.01274.
[27] D. Berthelot, T. Schumm, and L. Metz, “BEGAN: Boundary Equilibrium Generative Adversarial Networks,” 2017.
[28] A. van den Oord, O. Vinyals, and K. Kavukcuoglu, “Neural Discrete Representation Learning,” 2018.
[29] The 420. (2025). Bashe hacking group claims ICICI Bank data breach; ransom deadline Jan 24, 2025. The 420. Retrieved from https://www.the420.in/bashe-hacking-group-claims-icici-bank-data-breach-ransom-deadline-jan-24-2025
[30] Madras Pioneer. (2025). Security breaches leak student, employee data at 509J. Madras Pioneer. Retrieved from https://www.madraspioneer.com/townnews/software/security-breaches-leak-student-employee-data-at-509j/article_945830a8-d78a-11ef-aba1 f3909a813451.html
[31] Kaggle. (n.d.). NSL-KDD dataset. Retrieved from https://www.kaggle.com/datasets/hassan06/nslkdd.
[32] J. He, X. Wang, Y. Song, et al., “Network intrusion detection based on conditional wasserstein variational autoencoder with generative adversarial network and one-dimensional convolutional neural networks,” Applied Intelligence, vol. 53, no. 12, pp. 12416 12436, 2023. doi: 10.1007/s10489-022-03995-2.
[33] E. Redekop, M. Pleasure, Z. Wang, K. Sarma, A. Kinnaird, W. Speier, and C. Arnold, “Codebook VQ-VAE Approach for Prostate Cancer Diagnosis using Multiparametric MRI,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2365-2372, 2024.
