Open Access

ARTICLE

Optimal Deep Learning Based Ransomware Detection and Classification in the Internet of Things Environment

Manal Abdullah Alohali¹, Muna Elsadig¹, Fahd N. Al-Wesabi², Mesfer Al Duhayyim³, Anwer Mustafa Hilal^4,*, Abdelwahed Motwakel⁴

1 Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia
2 Department of Computer Science, College of Science & Art at Mahayil, King Khalid University, Saudi Arabia
3 Department of Computer Science, College of Sciences and Humanities- Aflaj, Prince Sattam bin Abdulaziz University, Saudi Arabia
4 Department of Computer and Self Development, Preparatory Year Deanship, Prince Sattam bin Abdulaziz University, AlKharj, Saudi Arabia

* Corresponding Author: Anwer Mustafa Hilal. Email:

Computer Systems Science and Engineering 2023, 46(3), 3087-3102. https://doi.org/10.32604/csse.2023.036802

Received 12 October 2022; Accepted 06 January 2023; Issue published 03 April 2023

Abstract

With the advent of the Internet of Things (IoT), several devices like sensors nowadays can interact and easily share information. But the IoT model is prone to security concerns as several attackers try to hit the network and make it vulnerable. In such scenarios, security concern is the most prominent. Different models were intended to address these security problems; still, several emergent variants of botnet attacks like Bashlite, Mirai, and Persirai use security breaches. The malware classification and detection in the IoT model is still a problem, as the adversary reliably generates a new variant of IoT malware and actively searches for compromise on the victim devices. This article develops a Sine Cosine Algorithm with Deep Learning based Ransomware Detection and Classification (SCADL-RWDC) method in an IoT environment. In the presented SCADL-RWDC technique, the major intention exists in recognizing and classifying ransomware attacks in the IoT platform. The SCADL-RWDC technique uses the SCA feature selection (SCA-FS) model to improve the detection rate. Besides, the SCADL-RWDC technique exploits the hybrid grey wolf optimizer (HGWO) with a gated recurrent unit (GRU) model for ransomware classification. A widespread experimental analysis is performed to exhibit the enhanced ransomware detection outcomes of the SCADL-RWDC technique. The comparison study reported the enhancement of the SCADL-RWDC technique over other models.

---

Keywords

---