
Number of Journals | 34 |
Number of Issues | 1,306 |
Number of Articles | 9,427 |
Article View | 9,188,348 |
PDF Download | 5,620,769 |
A model for Multi-Class Intrusion Detection Using the Dragonfly Feature Selection by Learning on the KDD-CUP99 Dataset | ||
پدافند الکترونیکی و سایبری | ||
Volume 10, Issue 3 - Serial Number 39, January 2023, Pages 33-42 PDF (1.16 M) | ||
Document Type: Original Article | ||
Authors | ||
Mahmoud niaei1; Jafar Tanha* 2; Gholamreza shahmohammadi3; Alireza poorebrahimi4 | ||
1PhD student in Information Technology Management Department, Department of Information Technology Management, Faculty of Management and Economics, Science and Research Unit, Islamic Azad University, Tehran, Iran | ||
2Associate Professor, Faculty of Electrical and Computer Engineering, Tabriz University, Tabriz, Iran | ||
3Associate Professor, Faculty of Electrical and Computer Engineering, Ivanki University, Semnan, Iran | ||
4Assistant Professor, Faculty of Management and Accounting, Karaj Branch, Islamic Azad University, Karaj, Iran | ||
Receive Date: 08 October 2021, Revise Date: 21 September 2022, Accept Date: 21 September 2022 | ||
Abstract | ||
With the increase of the network services, the number and complexity of attacks in cyberspace has increased. This problem has made network security as one of the most important challenges in the world of information technology. Intrusion detection systems are used as a very important defense method to detect network attacks, to warn network security admins.This research has proposed a model for multi-class intrusion detection system. In this model, the dragonfly algorithm is used for feature selection and the random forest algorithm is used for classification. for data analysis KDD-99 dataset has been used and the balancing operation was used. The model has been tested with different machine learning and deep learning algorithms then the best algorithm has been selected. The accuracy value in the proposed method is 99.83. The results have been compared with the results of several other studies published in authoritative articles. This comparison shows that the proposed method has a higher accuracy than most other methods. | ||
Keywords | ||
Intrusion Detection; Multi-class; Feature Selection; Dragonfly Algorithm; Random forest; KDD-CUP99 | ||
References | ||
[1] Hindy, H. & L. Jain, "A taxonomy and survey of intrusion detection system design techniques, network threats and datasets," " International Journal of Innovative Technology and Exploring Engineering (IJITEE), 5(2), pp. 298-309, 2018. [2] Mirjalili, S., "Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems," Neural Computing and Applications, 27(4), pp. 1053-1073, 2016. [3] Yahalom, R., "Improving the effectiveness of intrusion detection systems for hierarchical data. Knowledge-Based Systems," International Journal of Innovative Technology and Exploring Engineering (IJITEE), 5(4), pp. 59-69, 2019. [4] Farnaaz, N. & M. Jabbar, "Random forest modeling for network intrusion detection system. Procedia Computer Science," 89, pp. 213-217, 2016. [5] Kuang, F., W. Xu, & S. Zhang, "A novel hybrid KPCA and SVM with GA model for intrusion detection. Applied Soft Computing," 18, pp. 178-184, 2014. [6] Faker, O. & E. Dogdu. "Intrusion detection using big data and deep learning techniques," in Proceedings of the 2019 ACM Southeast Conference, 2019. [7] Mohammadi, S., "Cyber intrusion detection by combined feature selection algorithm," Journal of information security and applications, 44, pp. 80-88, 2019. [8] Choudhary, S. & N. Kesswani, "Analysis of KDD-Cup’99, NSL-KDD and UNSW-NB15 datasets using deep learning in IoT," Procedia Computer Science, 167, pp. 1561-1573, 2020. [9] Javaid, A., "A deep learning approach for network intrusion detection system," Eai Endorsed Transactions on Security and Safety, 3(9), p. e2, 2016. [10] Aishwarya, C., "Intrusion Detection System using KDD Cup 99 Dataset," International Journal of Innovative Technology and Exploring Engineering (IJITEE), 9(4), pp. 3169-3171, 2020. [11] Singh Panwar, S., Y. Raiwani, & L.S. Panwar. "Evaluation of network intrusion detection with features selection and machine learning algorithms on CICIDS-2017 dataset," in International Conference on Advances in Engineering Science Management & Technology (ICAESMT)-2019, Uttaranchal University, Dehradun, India. 2019. [12] Mafarja, M.M., "Binary dragonfly algorithm for feature selection," in 2017 International conference on new trends in computing sciences (ICTCS). 2017. IEEE. [13] Farnaaz, N. & M. Jabbar, "Random forest modeling for network intrusion detection system," Procedia Computer Science, 89, pp. 213-217, 2016. [14] Junker, M., R. Hoch, & A. Dengel. "On the evaluation of document analysis components by recall, precision, and accuracy," in Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR'99 (Cat. No. PR00318). 1999. IEEE. | ||
Statistics Article View: 301 PDF Download: 332 |