Open Access

ARTICLE

Voting Classifier and Metaheuristic Optimization for Network Intrusion Detection

Doaa Sami Khafaga¹, Faten Khalid Karim^1,*, Abdelaziz A. Abdelhamid^2,3, El-Sayed M. El-kenawy⁴, Hend K. Alkahtani¹, Nima Khodadadi⁵, Mohammed Hadwan⁶, Abdelhameed Ibrahim⁷

1 Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
2 Department of Computer Science, Faculty of Computer and Information Sciences, Ain Shams University, Cairo, 11566, Egypt
3 Department of Computer Science, College of Computing and Information Technology, Shaqra University, 11961, Saudi Arabia
4 Department of Communications and Electronics, Delta Higher Institute of Engineering and Technology, Mansoura, 35111, Egypt
5 The Department of Civil and Environmental Engineering, Florida International University, Miami, FL, USA
6 Department of Information Technology, College of Computer, Qassim University, Buraydah, 51452, Saudi Arabia
7 Computer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University, Mansoura, 35516, Egypt

* Corresponding Author: Faten Khalid Karim. Email:

Computers, Materials & Continua 2023, 74(2), 3183-3198. https://doi.org/10.32604/cmc.2023.033513

Received 19 June 2022; Accepted 11 August 2022; Issue published 31 October 2022

Abstract

Managing physical objects in the network’s periphery is made possible by the Internet of Things (IoT), revolutionizing human life. Open attacks and unauthorized access are possible with these IoT devices, which exchange data to enable remote access. These attacks are often detected using intrusion detection methodologies, although these systems’ effectiveness and accuracy are subpar. This paper proposes a new voting classifier composed of an ensemble of machine learning models trained and optimized using metaheuristic optimization. The employed metaheuristic optimizer is a new version of the whale optimization algorithm (WOA), which is guided by the dipper throated optimizer (DTO) to improve the exploration process ofthe traditional WOA optimizer. The proposed voting classifier categorizes the network intrusions robustly and efficiently. To assess the proposed approach, a dataset created from IoT devices is employed to record the efficiency of the proposed algorithm for binary attack categorization. The dataset records are balanced using the locality-sensitive hashing (LSH) and Synthetic Minority Oversampling Technique (SMOTE). The evaluation of the achieved results is performed in terms of statistical analysis and visual plots to prove the proposed approach’s effectiveness, stability, and significance. The achieved results confirmed the superiority of the proposed algorithm for the task of network intrusion detection.

---

Keywords

---