Deep learning has played a significant role in intrusion detection. However, deep learning-based intrusion detection methods require a large amount of annotated data for model training. In the real world, the types of intrusion data that are of concern often belong to minority classes that lack labels. This imbalance creates an imbalanced dataset for intrusion detection, where normal data significantly outweighs attack data. Class imbalance can lead to biased decision boundaries, resulting in increased classification errors for attack data. In the face of imbalanced data, we propose a data augmentation model based on VAE-WGAN-GP. VAE-WGAN-GP combines variational autoencoders (VAE) and Wasserstein generative adversarial networks (WGAN) with gradient penalty (GP), creating a deep learning generative model. We augment the minority class data using this model to balance the dataset. Finally, we demonstrate significant improvements in multi-class intrusion detection using multiple classifiers by applying our data augmentation model to a traditional internet dataset and an industrial control system network dataset.

Yahui Wang, Zhiyong Zhang. Industrial Internet Intrusion Detection Method Based on VAE-WGAN-GP Data Enhancement. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 4: 36-44. https://doi.org/10.25236/AJCIS.2024.070406.

[1] Park, K.J., Kim, J., Lim, H. and Eun, Y., 2014. Robust path diversity for network quality of service in cyber-physical systems. IEEE Transactions on Industrial Informatics, 10(4), pp.2204-2215.

[2] Kou, L., Ding, S., Rao, Y., Xu, W. and Zhang, J., 2022. A lightweight intrusion detection model for 5G-enabled industrial Internet. Mobile Networks and Applications, 27(6), pp.2449-2458.

[3] Yang, Y., Wu, L., Yin, G., Li, L. and Zhao, H., 2017. A survey on security and privacy issues in Internet-of-Things. IEEE Internet of things Journal, 4(5), pp.1250-1258.

[4] Malik, S., Amin, J., Sharif, M., Yasmin, M., Kadry, S. and Anjum, S., 2022. Fractured elbow classification using hand-crafted and deep feature fusion and selection based on whale optimization approach. Mathematics, 10(18), p.3291.

[5] Abu-Khzam, F.N., Abd El-Wahab, M.M., Haidous, M. and Yosri, N., 2022. Learning from obstructions: An effective deep learning approach for minimum vertex cover. Annals of Mathematics and Artificial Intelligence, pp.1-12.

[6] Sayour, M.H., Kozhaya, S.E. and Saab, S.S., 2022. Autonomous robotic manipulation: Real-time, deep-learning approach for grasping of unknown objects. Journal of Robotics, 2022.

[7] Wang, J., Li, P., Kong, W. and An, R., 2022. Unknown Security Attack Detection of Industrial Control System by Deep Learning. Mathematics, 10(16), p.2872.

[8] Khan, I.A., Keshk, M., Pi, D., Khan, N., Hussain, Y. and Soliman, H., 2022. Enhancing IIoT networks protection: A robust security model for attack detection in Internet Industrial Control Systems. Ad Hoc Networks, 134, p.102930.

[9] Krithivasan, K., Pravinraj, S. and VS, S.S., 2020. Detection of cyberattacks in industrial control systems using enhanced principal component analysis and hypergraph-based convolution neural network (EPCA-HG-CNN). IEEE Transactions on Industry Applications, 56(4), pp.4394-4404.

[10] Krawczyk, B., 2016. Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence, 5(4), pp.221-232.

[11] Zhou, X., Hu, Y., Wu, J., Liang, W., Ma, J. and Jin, Q., 2022. Distribution bias aware collaborative generative adversarial network for imbalanced deep learning in industrial IoT. IEEE Transactions on Industrial Informatics, 19(1), pp.570-580.

[12] Ahmad, Z., Shahid Khan, A., Wai Shiang, C., Abdullah, J. and Ahmad, F., 2021. Network intrusion detection system: A systematic study of machine learning and deep learning approaches. Transactions on Emerging Telecommunications Technologies, 32(1), p.e4150.

[13] Tomczak, J. and Welling, M., 2018, March. VAE with a VampPrior. In International conference on artificial intelligence and statistics PMLR. (pp. 1214-1223).

[14] Engelmann, J. and Lessmann, S., 2021. Conditional Wasserstein GAN-based oversampling of tabular data for imbalanced learning. Expert Systems with Applications, 174, p.114582.

[15] Safari, M., Parvinnia, E. and Haddad, A.K., 2021. Industrial intrusion detection based on the behavior of rotating machine. International Journal of Critical Infrastructure Protection, 34, p.100424.

[16] Sun, Y., Wang, G., Yan, P.Z., Zhang, L.F. and Yao, X., 2021, December. Industrial Control System Attack Detection Model Based on Bayesian Network and Timed Automata. In International Conference on Big Data (pp. 79-92). Cham: Springer International Publishing.

[17] Mbow, M., Koide, H. and Sakurai, K., 2021, November. An intrusion detection system for imbalanced dataset based on deep learning. In 2021 Ninth International Symposium on Computing and Networking (CANDAR) IEEE. (pp. 38-47). 

[18] Bao, F., Deng, Y., Kong, Y., Ren, Z., Suo, J. and Dai, Q., 2019. Learning deep landmarks for imbalanced classification. IEEE transactions on neural networks and learning systems, 31(8), pp.2691-2704.

[19] Liang, W., Hu, Y., Zhou, X., Pan, Y., Kevin, I. and Wang, K., 2021. Variational few-shot learning for microservice-oriented intrusion detection in distributed industrial IoT. IEEE Transactions on Industrial Informatics, 18(8), pp.5087-5095.

[20] Fu, Y., Du, Y., Cao, Z., Li, Q. and Xiang, W., 2022. A deep learning model for network intrusion detection with imbalanced data. Electronics, 11(6), p.898.

[21] Liu, L., Wang, P., Lin, J. and Liu, L., 2020. Intrusion detection of imbalanced network traffic based on machine learning and deep learning. IEEE access, 9, pp.7550-7563.

[22] Huang, S. and Lei, K., 2020. IGAN-IDS: An imbalanced generative adversarial network towards intrusion detection system in ad-hoc networks. Ad Hoc Networks, 105, p.102177.

[23] Ding, H., Chen, L., Dong, L., Fu, Z. and Cui, X., 2022. Imbalanced data classification: A KNN and generative adversarial networks-based hybrid approach for intrusion detection. Future Generation Computer Systems, 131, pp.240-254.