Purpose: These days, network security concerns are becoming more and more important due to the Internet's quick de-velopment. The goal of this article is to enhance the feature extraction and classification accuracy of network intrusion detection models by addressing the issues of low classification accuracy and weak generalization ability of current mod-els in the field. Methods: A deep learning network intrusion detection model and an LSTM model based on convolution-al neural networks (CNN) and weight dropout, abbreviated as AWD-CNN-LSTM, are creatively proposed. This model effectively extracts nonlinear features from the dataset using CNN, and temporal features from the dataset using LSTM. To alleviate overfitting caused by data imbalance, GP-GAN is introduced to oversample rare types of data, further en-hancing the model's generalization ability. The proposed intrusion detection model was experimentally tested on the NSL-KDD dataset. The experimental results showed that the proposed method has better accuracy compared to traditional ma-chine learning methods such as SVM and K-Means, as well as deep learning methods such as convolutional neural net-works, regardless of whether it is related to random forests. The improved accuracy and F1 score performance suggest that the IDS model suggested in this article has some practical value and can be used to enhance network security protection capabilities through network intrusion detection.
Keywords
Network Security, AWD-CNN-LSTM， GP-GAN, Deep Learning, Intrusion Detection Systems.
D. E. Denning, “An Intrusion-Detection Model,” IEEE Transactions on Software Engineering, vol. SE-13, no. 2, pp. 222–232, Feb. 1987, doi: 10.1109/tse.1987.232894.
A. Aldweesh, A. Derhab, and A. Z. Emam, “Deep learning approaches for anomaly-based intrusion detection systems: A survey, taxonomy, and open issues,” Knowledge-Based Systems, vol. 189, p. 105124, Feb. 2020, doi: 10.1016/j.knosys.2019.105124.
R. M. Elbasiony, E. A. Sallam, T. E. Eltobely, and M. M. Fahmy, “A hybrid network intrusion detection framework based on random forests and weighted k-means,” Ain Shams Engineering Journal, vol. 4, no. 4, pp. 753–762, Dec. 2013, doi: 10.1016/j.asej.2013.01.003.
A. Shubair, S. Ramadass, and A. A. Altyeb, “kENFIS: kNN-based evolving neuro-fuzzy inference system for computer worms detection,” Journal of Intelligent & Fuzzy Systems, vol. 26, no. 4, pp. 1893–1908, 2014, doi: 10.3233/ifs-130868.
Zhang Anlin, Zhang Qikun, Huang Daoying, etc, :Intrusion detection model based on CNN and BiGRU fusion neural network," Journal of Zhengzhou University (Engineering Edition), vol.43, no.3, pp.37-43, 2022.
T. Acharya, A. Annamalai, and M. F. Chouikha, “Efficacy of Bidirectional LSTM Model for Network-Based Anomaly Detection,” 2023 IEEE 13th Symposium on Computer Applications & Industrial Electronics (ISCAIE), vol. 2, pp. 336–341, May 2023, doi: 10.1109/iscaie57739.2023.10165336.
Tao Zhiyong, Yan Minghao, Liu Ying, "Channel coding closed set recognition based on temporal convolutional networks," Journal of Huazhong University of Science and Technology (Natural Science Edition), vol.50, no.3, pp.12-17, 2022.
A. Aldallal, “Toward Efficient Intrusion Detection System Using Hybrid Deep Learning Approach,” Symmetry, vol. 14, no. 9, p. 1916, Sep. 2022, doi: 10.3390/sym14091916.
M. Radhi Hadi and A. Saher Mohammed, “A Novel Approach to Network Intrusion Detection System using Deep Learning for SDN: Futuristic Approach,” Machine Learning & Applications, Jun. 2022, doi: 10.5121/csit.2022.121106.
S. Zheng, “Network Intrusion Detection Model Based on Convolutional Neural Network,” 2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Mar. 2021, doi: 10.1109/iaeac50856.2021.9390930.
Y. N. Rao and K. Suresh Babu, “An Imbalanced Generative Adversarial Network-Based Approach for Network Intrusion Detection in an Imbalanced Dataset,” Sensors, vol. 23, no. 1, p. 550, Jan. 2023, doi: 10.3390/s23010550.
M. Jamoos, A. García, M. AlKhanafseh, and O. Surakhi, “A New Data Balancing Approach based Generative Adversarial Network for Network Intrusion Detection System,” May 2023, doi: 10.20944/preprints202305.2218.v1.
J. Zhang and Y. Zhao, “Research on Intrusion Detection Method Based on Generative Adversarial Network,” 2021 International Conference on Big Data Analysis and Computer Science (BDACS), vol. 12, pp. 264–268, Jun. 2021, doi: 10.1109/bdacs53596.2021.00065.
K. Hemavathi and R. Latha, “Conditional Generative Adversarial Network with Optimal Machine Learning Based Intrusion Detection System,” 2023 International Conference on Sustainable Communication Networks and Application (ICSCNA), pp. 1176–1182, Nov. 2023, doi: 10.1109/icscna58489.2023.10370325.
R. Z. Farkhady, K. Majidzadeh, M. Masdari, and A. Ghaffari, “A novel feature selection algorithm for IoT networks intrusion detection system based on parallel CNN-LSTM model,” Mar. 2023, doi: 10.21203/rs.3.rs-2692168/v1.
Z. Ran, D. Zheng, Y. Lai, and L. Tian, “Applying Stack Bidirectional LSTM Model to Intrusion Detection,” Computers, Materials & Continua, vol. 65, no. 1, pp. 309–320, 2020, doi: 10.32604/cmc.2020.010102.
K. Saurabh et al., “LBDMIDS: LSTM Based Deep Learning Model for Intrusion Detection Systems for IoT Networks,” 2022 IEEE World AI IoT Congress (AIIoT), Jun. 2022, doi: 10.1109/aiiot54504.2022.9817245.
D. Jiawei, Y. Kai, H. Zhentao, J. Lingjie, H. Lei, and Y. Haixia, “Research on Intrusion Detection Algorithm Based on Optimized CNN-LSTM,” 2022 International Conference on Networking and Network Applications (NaNA), Dec. 2022, doi: 10.1109/nana56854.2022.00024.
B. Rudra and V. K. Agrawal, “Deep learning for network security: a novel GNN-LSTM-based intrusion detection model,” International Journal of Services, Economics and Management, vol. 1, no. 1, 2023, doi: 10.1504/ijsem.2023.10061342.
T. S. Harshitha, “Intrusion Detection and Prevention Using CNN-LSTM,” International Journal of Science, Engineering and Technology, vol. 12, no. 2, pp. 1–6, Feb. 2024, doi: 10.61463/ijset.vol.12.issue2.125.
H. Karamollaoğlu, İ. Yücedağ, and İ. A. Doğru, “A Hybrid PCA-MAO Based LSTM Model for Intrusion Detection in IoT Environments,” Dec. 2022, doi: 10.21203/rs.3.rs-2357212/v1.
H. C. Altunay and Z. Albayrak, “A hybrid CNN+LSTM-based intrusion detection system for industrial IoT networks,” Engineering Science and Technology, an International Journal, vol. 38, p. 101322, Feb. 2023, doi: 10.1016/j.jestch.2022.101322.
S. Solanki, C. Gupta, and K. Rai, “A Survey on Machine Learning based Intrusion Detection System on NSL-KDD Dataset,” International Journal of Computer Applications, vol. 176, no. 30, pp. 36–39, Jun. 2020, doi: 10.5120/ijca2020920343.
A. Shehadeh, H. ALTaweel, and A. Qusef, “Analysis of Data Mining Techniques on KDD-Cup’99, NSL-KDD and UNSW-NB15 Datasets for Intrusion Detection,” 2023 24th International Arab Conference on Information Technology (ACIT), vol. 2, pp. 1–6, Dec. 2023, doi: 10.1109/acit58888.2023.10453884.
S. Walling and S. Lodh, “Performance Evaluation of Supervised Machine Learning Based Intrusion Detection with Univariate Feature Selection on NSL KDD Dataset,” Feb. 2023, doi: 10.21203/rs.3.rs-2537820/v1.
Acknowledgements
The authors would like to thank to the reviewers for nice comments on the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Baoguo Liu, Eric B. Blancaflor and Mideth Abisado, “Research on Improved LSTM and Deep Learning Intrusion Detection Algorithms”, Journal of Machine and Computing. doi: 10.53759/7669/jmc202505006.
