Network security is becoming more and more important as a result of the growing use of the internet and technological developments. Intrusion Detection Systems (IDS) are utilized to detect attacks, preferably by monitoring real-time events. Therefore, they hold a significant position in network security. By detecting network attacks based on anomalies, IDSs can ensure network security. Deep learning (DL) can be used to create efficient intrusion detection systems. In this study, three different intrusion detection systems are proposed using Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and their hybrid combination, CNN-LSTM. Deep learning models have complex structures and require adjustment of various hyperparameters, which can be time-consuming when done manually. To address this issue, particle swarm optimization (PSO) is employed in this study for hyperparameter optimization. PSO automatically selects hyperparameters and enhances performance. The CIC-IDS2017 dataset is used to validate the approaches. Models are evaluated with different performance metrics including accuracy, recall, precision, false alarm rate, F1-score, and error rate. The hybrid CNN-LSTM model performs better than other models due to its ability to capture both temporal and spatial features simultaneously. Consequently, the results clearly illustrate the significance and impacts of hyperparameter optimization in intrusion detection systems.

Keywords - Deep learning, Intrusion Detection Systems, Particle Swarm Optimization, Hyperparameter optimization, CIC-IDS 2017

[1] P. Mishra, V. Varadharajan, E.S. Pilli “A detailed investigation and analysis of using machine learning techniques for intrusion detection”, IEEE Communications Surveys & Tutorials, vol.21, pp. (99)1:1, June. 2018.

[2] P. Sun, P. Liu, Q. Li, C. Liu, X. Lu, R. Hao, J. Chen, “DL-IDS: extracting features using CNN-LSTM hybrid network for intrusion detection system”, Security and Communication Networks, vol. 20, pp. 1-11, 2020.

[3] M. Jenckel, S.S. Bukhari, “Training LSTM-RNN with imperfect transcription: limitations and outcomes,” in The 4th international workshop on historical document imaging and processing, 2017, paper 48-53.

[4] Erden E, Demir İE, Kökçam AH. “Enhancing Machine Learing Model Performance With Hyper Parameter Optimization”, 2023

[5] M. Choraś, and M. Pawlicki, “Intrusion detection approach based on optimised artificial neural network”, Neurocomputing,vol. 452, pp.705-715, Sep., 2021

[6] Z.K. Maseer, R. Yusof, N. Bahaman, S.A. Mostafa and C.F.M Foozy, “Benchmarking of machine learning for anomaly based intrusion detection systems in the CICIDS2017 dataset”, IEEE Access, Feb, 2021

[7] J. Jose, D.V. Jose, “Deep learning algorithms for intrusion detection systems in internet of things using CIC-IDS 2017 dataset”, International Journal of Electrical and Computer Engineering (IJECE), 2022, paper 1134-1141.

[8] J. Gao,, S. Chai, B. Zhang, and Y. Xia “Research on network intrusion detection based on incremental extreme learning machine and adaptive principal component analysis”, Energies, vol.12(7), pp. 1–17, March, 2019.

[9] W. Zheng, “Intrusion detection based on convolutional neural network”, International Conference on Computer Engineering and Application (ICCEA), 2020

[10] M. A. Khan, “HCRNNIDS: hybrid convolutional recurrent neural network-based network intrusion detection system”, Processes ,vol. 9, pp. 834, 2021.

[11] W. Elmasry, A. Akbulut and A.H. Zalim, “Evoling deep learning architectures for network intrusion detection using a double PSO metaheuristic”, Computer Networks, vol.168, 2020.

[12] Y. Xın, L. Kong, Z. Lıu, Y. Chen, Y. Lı, H. Zhu, M. Gao, H. Hou and C. Wang, “Machine learning and deep learning methods for cybersecurity”, Ieee Access, vol.6, July, 2018.

[13] J. Gu, Z. Wang, J. Kuen, L. Ma,, A. Shahroudy, B. Shuai, T. Liu, X. Wang, G. Wang, J. Cai, T. Chen, “Recent advances in convolutional neural networks”, Pattern Recognition, vol.77, pp.354-377, May, 2018.

[14] G. V. Houdt, C. Mosquera and G. Nápoles, G, “A review on the long short-term memory model” Artificial Intelligence Review, vol.53(8), pp. 5929-5955, May, 2020

[15] T. Le, J. Kim, “An effective intrusion detection classifier using long short-term memory with gradient descent optimization” in 2017 International Conference on Platform Technology and Service (PlatCon), 2017, pp. 1-6

[16] A. Halbouni,, T. S. Gunawan., M. H. Habaebi, M. Halbouni, M. Kartiwi, R. Ahmad, “CNN-LSTM: hybrid deep neural network for network intrusion detection system” IEEE Access, 2017.

[17] Y. Shi, “Particle swarm optimization: developments, applications and resources” in Proceedings of the 2001 congress on evolutionary computation, 2001, pp. 81-86).

[18] Z. Vujović, ”Classification model evaluation metrics”, International Journal of Advanced Computer Science and Applications, vol. 12(6), pp. 599-606, 2021.

[19] J. Jose and D. V. Jose, “Deep learning algorithms for intrusion detection systems in internet of things using CIC-IDS 2017 dataset”, International Journal of Electrical and Computer Engineering (IJECE), vol. 13(1), pp. 1134-1141, 2023.

[20] A. Yulianto, P. Sukarno, and N. A. Suwastika, ‘‘Improving AdaBoost- based intrusion detection system (IDS) performance on CIC IDS 2017 dataset,’’, Journal of Physics Conference Series, 2019.

[21] Z. Pelletier and M. Abualkibash,” Evaluating the CIC IDS-2017 dataset using machine learning methods and creating multiple predictive models in the statistical computing language R”, International Research Journal of Advanced Engineering and Science, 2020, paper. 187-191.