Hybrid Deep Learning Framework For Robust Network Traffic Classification
DOI:
https://doi.org/10.29284/82c2vq04Keywords:
network traffic prediction; KDD; CNN; bidirectional LSTM.Abstract
As network traffic is growing at a fast rate, it is important to predict future traffic patterns in order to manage and optimize the network. This study provides a hybrid deep learning architecture, which is a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks and which can improve the accuracy of network traffic prediction. The feature extraction uses CNN that captures spatial dependencies in the data and the temporal dependencies are captured by using LSTM that allows the framework to successfully learn long-term trends in network traffic. The proposed hybrid model is better than the classical deep learning model, which relies on the ability of CNN to obtain the required characteristics and the power of LSTM to analyze sequential dependencies. The framework is far superior to the current deep learning models in that it has solved the problem of complexity of feature extraction and also sequence learning, which makes it a formidable tool in the real-time network traffic prediction. The KDD dataset of network traffic prediction is used to implement the proposed model. The proposed model is tested regarding accuracy, precision, and recall. The findings prove that the hybrid CNNLSTM model with an accuracy of 98% are accompanied by a precision of 97% and a recall of 96% meaning that the model has a high capacity to detect normal and attack traffic correctly. The proposed method also presents a significant improvement over the baseline deep learning models in the detection of minority attack classes, which, in turn, confirms its practical use in the real world.
References
[1] Alam, F., Kashef, R., and Jaseemuddin, M., 2021. Enhancing the performance of network traffic classification methods using efficient feature selection models. In 2021 IEEE International Systems Conference (SysCon), pp. 1-6.
[2] Poriye, M., and Upadhyaya, S., 2023. Hybrid classification model for network traffic density estimation. In 2023 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), pp. 1051-1056.
[3] Adeke, J.M., Chen, J., Zhang, L., Mensah, R.N., and Tong, K., 2020. An efficient approach based on parameter optimization for network traffic classification using machine learning. In 2020 7th International Conference on Dependable Systems and Their Applications (DSA), pp. 99-107.
[4] Shi, S., Guo, Y., Wang, D., Zhu, Y., and Han, Z., 2023. Distributionally robust federated learning for network traffic classification with noisy labels. IEEE Transactions on Mobile Computing, 23(5), pp. 6212-6226.
[5] Liu, H., and Lang, B., 2021. Network traffic classification method supporting unknown protocol detection. In 2021 IEEE 46th Conference on Local Computer Networks (LCN), pp. 311-314.
[6] Ariffin, A., Zaki, F., and Anuar, N.B., 2023. Leveraging federated learning and xai for privacy-aware and lightweight edge training in network traffic classification. In 2023 IEEE International Conference on Computing (ICOCO), pp. 47-52.
[7] Fosić, I., Žagar, D., and Grgić, K., 2022. Network traffic verification based on a public dataset for IDS systems and machine learning classification algorithms. In 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO), pp. 1037-1041.
[8] Usama, M., Qayyum, A., Qadir, J., and Al-Fuqaha, A., 2019. Black-box adversarial machine learning attack on network traffic classification. In 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), pp. 84-89.
[9] Wang, C., Xu, T., and Qin, X., 2015. Network traffic classification with improved random forest. In 2015 11th International Conference on Computational Intelligence and Security (CIS), pp. 78-81.
[10] Hussain, M.M.K.A., Jaseemuddin, M., and Kashef, R., 2023. Network traffic classification using distributed ML-based data parallelization approach. In 2023 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pp. 539-546.
[11] Wei, S., Chen, X., and Zhou, B., 2018. Network traffic classification based on AR-ELM algorithm. In 2018 13th World Congress on Intelligent Control and Automation (WCICA), pp. 1500-1505.
[12] Bader, O., Lichy, A., Dvir, A., Dubin, R., and Hajaj, C., 2024. OSF-EIMTC: an open-source framework for standardized encrypted internet traffic classification. Computer Communications, 213, pp. 271-284.
[13] Geng, Y., Cai, S., Qin, S., Chen, H., and Yin, S., 2021. An efficient network traffic classification method based on combined feature dimensionality reduction. In 2021 IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS C), pp. 407-414.
[14] Wang, X., Chen, S., and Su, J., 2020. App-net: A hybrid neural network for encrypted mobile traffic classification. In IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp. 424-429.
[15] Koumar, J., Hynek, K., and Čejka, T., 2023. Network traffic classification based on single flow time series analysis. In 2023 19th International Conference on Network and Service Management (CNSM), pp. 1-7.
[16] Mishra, S., and Manam, V.C., 2023. A comparative study of unsupervised learning techniques and natural language processing in network traffic classification. In 2023 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), pp. 138-143.
[17] Abbasi, M., Florez, S.L., Shahraki, A., Taherkordi, A., Prieto, J., and Corchado, J.M., 2025. Class imbalance in network traffic classification: an adaptive weight ensemble-of-ensemble learning method. IEEE Access.
[18] Wang, X., Wang, Y., Lai, Y., Hao, Z., and Liu, A.X., 2025. Reliable open-set network traffic classification. IEEE Transactions on Information Forensics and Security.
[19] Lin, W., and Chen, Y., 2024. Robust network traffic classification based on information bottleneck neural network. IEEE Access.
[20] Hu, G., Xiao, X., Shen, M., Zhang, B., Yan, X., and Liu, Y., 2023. TCGNN: packet-grained network traffic classification via graph neural networks. Engineering Applications of Artificial Intelligence, 123, 106531.
[21] Wang, Y., Yun, X., Zhang, Y., Zhao, C., and Liu, X., 2022. A multi-scale feature attention approach to network traffic classification and its model explanation. IEEE Transactions on Network and Service Management, 19(2), pp. 875-889.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
