Open Access

ARTICLE

A New Hybrid Approach Using GWO and MFO Algorithms to Detect Network Attack

by Hasan Dalmaz^*, Erdal Erdal, Halil Murat Ünver

Department of Computer Engineering, Faculty of Engineering and Architecture, Kırıkkale University, Kırıkkale, 71450, Turkey

* Corresponding Author: Hasan Dalmaz. Email:

Computer Modeling in Engineering & Sciences 2023, 136(2), 1277-1314. https://doi.org/10.32604/cmes.2023.025212

Received 28 June 2022; Accepted 30 September 2022; Issue published 06 February 2023

Abstract

This paper addresses the urgent need to detect network security attacks, which have increased significantly in recent years, with high accuracy and avoid the adverse effects of these attacks. The intrusion detection system should respond seamlessly to attack patterns and approaches. The use of metaheuristic algorithms in attack detection can produce near-optimal solutions with low computational costs. To achieve better performance of these algorithms and further improve the results, hybridization of algorithms can be used, which leads to more successful results. Nowadays, many studies are conducted on this topic. In this study, a new hybrid approach using Gray Wolf Optimizer (GWO) and Moth-Flame Optimization (MFO) algorithms was developed and applied to widely used data sets such as NSL-KDD, UNSW-NB15, and CIC IDS 2017, as well as various benchmark functions. The ease of hybridization of the GWO algorithm, its simplicity, its ability to perform global optimal search, and the success of the MFO algorithm in obtaining the best solution suggested that an effective solution would be obtained by combining these two algorithms. For these reasons, the developed hybrid algorithm aims to achieve better results by using the good aspects of both the GWO algorithm and the MFO algorithm. In reviewing the results, it was found that a high level of success was achieved in the benchmark functions. It achieved better results in 12 of the 13 benchmark functions compared. In addition, the success rates obtained according to the evaluation criteria in the different data sets are also remarkable. Comparing the 97.4%, 98.3%, and 99.2% classification accuracy results obtained in the NSL-KDD, UNSW-NB15, and CIC IDS 2017 data sets with the studies in the literature, they seem to be quite successful.

---

Keywords

---