A PREPROCESSING PIPELINE FOR IMAGE CONSTRUCTION IN CNN-BASED MULTICLASS INTRUSION DETECTION
Main Article Content
Abstract
Recent studies have applied deep learning methods, such as convolutional neural networks (CNNs), to structured network traffic by representing the data as images for intrusion detection. Multiclass intrusion detection using these representations faces challenges because class distributions are imbalanced and features differ in scale. We propose a sequential preprocessing pipeline to convert network traffic data into images for CNN-based intrusion detection systems. The pipeline combines categorical variable encoding, adaptive synthetic sampling (ADASYN) to address class imbalance, and base-256 decomposition to preserve precision in large numerical fields. Evaluation using the NSL-KDD dataset and the independent KDDTest+ test set shows that systematic preprocessing improves multiclass detection performance.
Keywords
Data preprocessing, NSL-KDD, CNN
Article Details
References
Aldweesh, A., Derhab, A., & Emam, A. Z. (2019). Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues. Knowledge-Based Systems, 189, 105124.
Al-Qatf, M., Lasheng, Y., Al-Habib, M., & Al-Sabahi, K. (2018). Deep learning approach combining sparse autoencoder with SVM for network intrusion detection. IEEE Access, 6, 52843–52856.
Al-Turaiki, I., & Altwaijry, N. (2021). A convolutional neural network for improved anomaly-based network intrusion detection. Cybersecurity, 4(3).
Altwaijry, N., Alqahtani, A., & Al-Turaiki, I. (2020). A deep learning approach for anomaly-based network intrusion detection. In Y. Tian, T. Ma, & M. K. Khan (Eds.), Proceedings of the First International Conference on Big Data and Security. Springer.
Dhanabal, L., & Shantharajah, S. (2015). A study on NSL-KDD dataset for intrusion detection system based on classification algorithms. International Journal of Advanced Research in Computer and Communication Engineering, 4(6), 446–452.
Ha, T. D., & Nguyen, H. S. (2023). A data preprocessing method prior to imaging for CNN-based intrusion detection. In Proceedings of the 26th National Conference on Electronics, Communications and Information Technology (REV-ECIT 2023) (pp. 311–316). https://rev-ecit.vn/vi/content/ky-yeu-hoi-nghi-0
Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2019). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 50, 102419.
He, H., Bai, Y., Garcia, E. A., & Li, S. (2008). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In Proceedings of the IEEE International Joint Conference on Neural Networks (pp. 1322–1328). IEEE.
Huynh, A. T., Nguyen, B.-T., Nguyen, H.-T., Vu, S., & Nguyen, H. D. (2021). A method of deep reinforcement learning for simulation of autonomous vehicle control. In Proceedings of the 16th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE 2021) (pp. 372–379). SciTePress. https://doi.org/10.5220/0010478903720379
Iftikhar, N., Rehman, M. U., Shah, M. A., Alenazi, M. J. F., & Ali, J. (2025). Intrusion detection in NSL-KDD dataset using hybrid self-organizing map model. Computer Modeling in Engineering & Sciences, 143(1), 639–671.
Jang, J., An, Y., Kim, D., & Choi, D. (2023). Feature importance-based backdoor attack in NSL-KDD. Electronics, 12(24), 4953. https://doi.org/10.3390/electronics12244953
Liu, H., & Lang, B. (2019). Machine learning and deep learning methods for intrusion detection systems: A survey. Applied Sciences, 9(20), 4396.
Masum, M., Shahriar, H., & Haddad, H. M. (2021). A transfer learning with deep neural network approach for network intrusion detection. International Journal of Intelligent Computing Research, 12(1), 1087–1095.
NSL-KDD Dataset. (n.d.). NSL-KDD intrusion detection dataset. https://www.unb.ca/cic/datasets/nsl.html
Patel, R. (2023, August 9). Protecting against sophisticated cyberattacks requires layered defenses. Forbes Technology Council.
Potdar, K. (2017). A comparative study of categorical variable encoding techniques for neural network classifiers. International Journal of Computer Applications, 175(4).
Sherin, V. J. I. J., & Radhika, N. (2022). Stacked ensemble IDS using NSL-KDD dataset. Journal of Pharmaceutical Negative Results, 13(3).
Tama, B. A., Comuzzi, M., & Rhee, K.-H. (2019). TSE-IDS: A two-stage classifier ensemble for intelligent anomaly-based intrusion detection system. IEEE Access, 7, 94497–94507.
Tavallaee, M., Bagheri, E., Lu, W., & Ghorbani, A. A. (2009). A detailed analysis of the KDD Cup 99 data set. In Proceedings of the IEEE Symposium on Computational Intelligence for Security and Defense Applications (pp. 1–6). IEEE.
Thaseen, I. S., & Kumar, C. A. (2017). Intrusion detection model using fusion of chi-square feature selection and multiclass SVM. Journal of King Saud University – Computer and Information Sciences, 29(4), 462–472.
Tran, N. N. D., Nguyen, H. D., Huynh, N. T., Tran, N. P., & Nguyen, L. V. (2022). Segmentation on chest CT imaging in COVID-19 based on the improvement Attention U-Net model. In New trends in intelligent software methodologies, tools and techniques (Vol. 355, pp. 596–606). IOS Press. https://doi.org/10.3233/FAIA220288
Vinayakumar, R., Alazab, M., Soman, K. P., Poornachandran, P., Al-Nemrat, A., & Venkatraman, S. (2019). Deep learning approach for intelligent intrusion detection system. IEEE Access, 7, 41525–41550.
Wisanwanichthan, T., & Thammawichai, M. (2025). A lightweight intrusion detection system for IoT and UAV using deep neural networks with knowledge distillation. Computers, 14(7). https://doi.org/10.3390/computers14070291
Wu, Y., & Hu, X. (2022). An intrusion detection method based on fully connected recurrent neural network. Scientific Programming, 2022, 1–11. https://doi.org/10.1155/2022/7777211
Yin, C., Zhu, Y., Fei, J., & He, X. (2017). A deep learning approach for intrusion detection using recurrent neural networks. IEEE Access, 5, 21954–21961.
Zhou, L., Pan, S., Wang, J., & Vasilakos, A. V. (2017). Machine learning on big data: Opportunities and challenges. Neurocomputing, 237, 350–361.
Al-Qatf, M., Lasheng, Y., Al-Habib, M., & Al-Sabahi, K. (2018). Deep learning approach combining sparse autoencoder with SVM for network intrusion detection. IEEE Access, 6, 52843–52856.
Al-Turaiki, I., & Altwaijry, N. (2021). A convolutional neural network for improved anomaly-based network intrusion detection. Cybersecurity, 4(3).
Altwaijry, N., Alqahtani, A., & Al-Turaiki, I. (2020). A deep learning approach for anomaly-based network intrusion detection. In Y. Tian, T. Ma, & M. K. Khan (Eds.), Proceedings of the First International Conference on Big Data and Security. Springer.
Dhanabal, L., & Shantharajah, S. (2015). A study on NSL-KDD dataset for intrusion detection system based on classification algorithms. International Journal of Advanced Research in Computer and Communication Engineering, 4(6), 446–452.
Ha, T. D., & Nguyen, H. S. (2023). A data preprocessing method prior to imaging for CNN-based intrusion detection. In Proceedings of the 26th National Conference on Electronics, Communications and Information Technology (REV-ECIT 2023) (pp. 311–316). https://rev-ecit.vn/vi/content/ky-yeu-hoi-nghi-0
Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2019). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 50, 102419.
He, H., Bai, Y., Garcia, E. A., & Li, S. (2008). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In Proceedings of the IEEE International Joint Conference on Neural Networks (pp. 1322–1328). IEEE.
Huynh, A. T., Nguyen, B.-T., Nguyen, H.-T., Vu, S., & Nguyen, H. D. (2021). A method of deep reinforcement learning for simulation of autonomous vehicle control. In Proceedings of the 16th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE 2021) (pp. 372–379). SciTePress. https://doi.org/10.5220/0010478903720379
Iftikhar, N., Rehman, M. U., Shah, M. A., Alenazi, M. J. F., & Ali, J. (2025). Intrusion detection in NSL-KDD dataset using hybrid self-organizing map model. Computer Modeling in Engineering & Sciences, 143(1), 639–671.
Jang, J., An, Y., Kim, D., & Choi, D. (2023). Feature importance-based backdoor attack in NSL-KDD. Electronics, 12(24), 4953. https://doi.org/10.3390/electronics12244953
Liu, H., & Lang, B. (2019). Machine learning and deep learning methods for intrusion detection systems: A survey. Applied Sciences, 9(20), 4396.
Masum, M., Shahriar, H., & Haddad, H. M. (2021). A transfer learning with deep neural network approach for network intrusion detection. International Journal of Intelligent Computing Research, 12(1), 1087–1095.
NSL-KDD Dataset. (n.d.). NSL-KDD intrusion detection dataset. https://www.unb.ca/cic/datasets/nsl.html
Patel, R. (2023, August 9). Protecting against sophisticated cyberattacks requires layered defenses. Forbes Technology Council.
Potdar, K. (2017). A comparative study of categorical variable encoding techniques for neural network classifiers. International Journal of Computer Applications, 175(4).
Sherin, V. J. I. J., & Radhika, N. (2022). Stacked ensemble IDS using NSL-KDD dataset. Journal of Pharmaceutical Negative Results, 13(3).
Tama, B. A., Comuzzi, M., & Rhee, K.-H. (2019). TSE-IDS: A two-stage classifier ensemble for intelligent anomaly-based intrusion detection system. IEEE Access, 7, 94497–94507.
Tavallaee, M., Bagheri, E., Lu, W., & Ghorbani, A. A. (2009). A detailed analysis of the KDD Cup 99 data set. In Proceedings of the IEEE Symposium on Computational Intelligence for Security and Defense Applications (pp. 1–6). IEEE.
Thaseen, I. S., & Kumar, C. A. (2017). Intrusion detection model using fusion of chi-square feature selection and multiclass SVM. Journal of King Saud University – Computer and Information Sciences, 29(4), 462–472.
Tran, N. N. D., Nguyen, H. D., Huynh, N. T., Tran, N. P., & Nguyen, L. V. (2022). Segmentation on chest CT imaging in COVID-19 based on the improvement Attention U-Net model. In New trends in intelligent software methodologies, tools and techniques (Vol. 355, pp. 596–606). IOS Press. https://doi.org/10.3233/FAIA220288
Vinayakumar, R., Alazab, M., Soman, K. P., Poornachandran, P., Al-Nemrat, A., & Venkatraman, S. (2019). Deep learning approach for intelligent intrusion detection system. IEEE Access, 7, 41525–41550.
Wisanwanichthan, T., & Thammawichai, M. (2025). A lightweight intrusion detection system for IoT and UAV using deep neural networks with knowledge distillation. Computers, 14(7). https://doi.org/10.3390/computers14070291
Wu, Y., & Hu, X. (2022). An intrusion detection method based on fully connected recurrent neural network. Scientific Programming, 2022, 1–11. https://doi.org/10.1155/2022/7777211
Yin, C., Zhu, Y., Fei, J., & He, X. (2017). A deep learning approach for intrusion detection using recurrent neural networks. IEEE Access, 5, 21954–21961.
Zhou, L., Pan, S., Wang, J., & Vasilakos, A. V. (2017). Machine learning on big data: Opportunities and challenges. Neurocomputing, 237, 350–361.