Open Access

ARTICLE

Enhanced Metaheuristics with Machine Learning Enabled Cyberattack Detection Model

Ahmed S. Almasoud^*

Department of Information Systems, College of Computer and Information Sciences, Prince Sultan University, Riyadh, 12435, Saudi Arabia

* Corresponding Author: Ahmed S. Almasoud. Email:

Intelligent Automation & Soft Computing 2023, 37(3), 2849-2863. https://doi.org/10.32604/iasc.2023.039718

Received 13 February 2023; Accepted 14 April 2023; Issue published 11 September 2023

Abstract

The Internet of Things (IoT) is considered the next-gen connection network and is ubiquitous since it is based on the Internet. Intrusion Detection System (IDS) determines the intrusion performance of terminal equipment and IoT communication procedures from IoT environments after taking equivalent defence measures based on the identified behaviour. In this background, the current study develops an Enhanced Metaheuristics with Machine Learning enabled Cyberattack Detection and Classification (EMML-CADC) model in an IoT environment. The aim of the presented EMML-CADC model is to detect cyberattacks in IoT environments with enhanced efficiency. To attain this, the EMML-CADC model primarily employs a data preprocessing stage to normalize the data into a uniform format. In addition, Enhanced Cat Swarm Optimization based Feature Selection (ECSO-FS) approach is followed to choose the optimal feature subsets. Besides, Mayfly Optimization (MFO) with Twin Support Vector Machine (TSVM), called the MFO-TSVM model, is utilized for the detection and classification of cyberattacks. Here, the MFO model has been exploited to fine-tune the TSVM variables for enhanced results. The performance of the proposed EMML-CADC model was validated using a benchmark dataset, and the results were inspected under several measures. The comparative study concluded that the EMML-CADC model is superior to other models under different measures.

---

Keywords

---