2025 Vol.8 Jun.N03

• Title: Research on Performance Optimization of Network Intrusion Detection System Using Fused CNN and BiLSTM
• Name: XiangMing Gou 12 , Md Gapar Md Johar2* , Jacquline Tham3
• Company: 1.School of Information Engineering, GongQing Institute of Science and Technology, Jiujiang Jiangxi, 332020, China 2. Software Engineering and Digital Innovation Centre, Management and Science University, Shah Alam, Selangor, 40100, Malaysia 3.Postgradua
• Abstract:

   With the rapid development of the Internet, network security has become a significant concern for organizations and individuals alike. Network Intrusion Detection Systems (NIDS) play a crucial role in safeguarding network environments by identifying and responding to malicious activities. Traditional NIDS, however, often struggle with high false positive rates, low detection accuracy, and inefficiency in handling large-scale network traffic. To address these challenges, this paper proposes a novel NIDS that fuses Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks. This hybrid model leverages the strengths of CNN in feature extraction and BiLSTM in capturing temporal dependencies, aiming to enhance the performance of NIDS. Extensive experiments are conducted on the KDD CUP 99 dataset to evaluate the effectiveness of the proposed model. The results demonstrate that the fused CNN-BiLSTM model outperforms traditional machine learning algorithms and standalone deep learning models in terms of detection accuracy, precision, recall, and F1-score. This research contributes to the advancement of NIDS by providing a robust and efficient solution for network intrusion detection.

  
  

• Keyword: Network Intrusion Detection System (NIDS), Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), performance optimization, KDD CUP 99 dataset.
• DOI: 10.12250/jpciams2025090602
• Citation form: XiangMing Gou, Md Gapar Md Johar, Jacquline Tham.Research on Performance Optimization of Network Intrusion Detection System Using Fused CNN and BiLSTM[J]. Computer Informatization and Mechanical System,2025,Vol.8,pp.5-10

[1] Denning, D. E. (1987). An intrusion-detection model. IEEE Transactions on Software Engineering, (2), 222-232.

[2] Lunt, T. F., Jagannathan, R., Lee, R., & Gilham, F. (1993). IDES: The enhanced intrusion detection expert system. In SRI International, Computer Science Laboratory (Vol. 93-09).

[3] Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill.

[4] Dietterich, T. G. (1997). Ensemble methods in machine learning. In Proceedings of the International Workshop on Multiple Classifier Systems (pp. 1-15). Springer, Berlin, Heidelberg.

[5] Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554.

[6] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 1097-1105.

[7] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

[8] Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.

[9] Zhou, T., & Zhang, H. (2024). Research on network intrusion detection method based on deep learning. Journal of Cloud Computing, 10(1), 1-12.

[10] Thaljaoui, A. (2025). Intelligent network intrusion detection system using optimized deep CNN-LSTM with UNSW-NB15. Journal of Information Security and Applications, 62, 103061.

[11] Liu, H., & Li, L. (2023). A network intrusion detection method based on deep learning. Computers & Security, 127, 102954.

[12] Yeung, D. Y., & Ding, Y. (2003). Host-based intrusion detection using dynamic and static behavioral models. Pattern Recognition, 36(1), 229-243.

[13] Shiravi, A., Shiravi, H., Tavallaee, M., & Ghorbani, A. A. (2012). Toward developing a systematic approach to generate benchmark datasets for intrusion detection. Computers & Security, 31(3), 357-374.

[14] Paxson, V. (1999). Bro: A system for detecting network intruders in real-time. Computer Networks, 31(10), 2435-2463.

[15] Salah, S., Maciá-Fernández, G., & Díaz-Verdejo, J. E. (2013). A model-based survey of alert correlation techniques. Computer Networks, 57(5), 1289-1317.

[16] Lee, W., Miller, M., Stolfo, S. J., Fan, W., & Zadok, E. (2002). Toward cost-sensitive modeling for intrusion detection and response. Journal of Computer Security, 10(3), 5-22.

[17] Cheng, T. H., Lin, Y. D., Lai, Y. C., & Lin, P. C. (2012). Evasion techniques: Sneaking through your intrusion detection/prevention systems. IEEE Communications Surveys & Tutorials, 14(4), 1011-1020.

[18] Zhu, M., & Zhang, Y. (2020). Research on network intrusion detection based on deep belief network. Journal of Computer and Communications, 8(05), 45-52.

[19] Zhang, H., & Zhou, T. (2024). Network intrusion detection method combining CNN and BiLSTM in cloud computing environment. International Journal of Advanced Computer Science and Applications, 15(5), 1-11.

[20] Thaljaoui, A., & Abdelaziz, F. (2024). Intelligent network intrusion detection system using optimized deep CNN-LSTM with UNSW-NB15. Journal of Information Security and Applications, 62, 103061.