Detection of Mirai Malware Attacks in IoT Environments Using Random Forest Algorithms

Abstract

The potential for Cyber-attacks against Internet of Thing (IoT) Infrastructure is enormous as devices run on pre-existing network infrastructure, for example Mirai Malware Attack. Network Forensics investigations require the Random Forest Algorithm which is used to perform classification and detection techniques for the Mirai Malware attack. The trials have been carried out using 5 attack scenarios and device types. The experimental results show that the RF algorithm achieves optimal performance with an average accuracy value of 95.01%, recall 90.82%, F1 Score 93.85% and the best precision value 99.23%. Besides, the Random Forest algorithm is suitable for very large data processing. The contribution of this research is to provide a recommendation that the RF Algorithm can be used to classify and identify Mirai malware attacks on the Internet of Things infrastructure.