Malware Classification Using Machine Learning Algorithm

Abstract

The rise of malware has resulted in many concerns and trends for future cybercriminals that infect victims' computers to steal information. The majority of the devices are highly vulnerable to simple attacks based on weak passwords, unpatched vulnerabilities, and poorly monitored. Thus, it is the best projection that computers nowadays being the main target to propagate malware. Besides, there is a lack of studies that provide in-depth analysis on malware, especially in the classification model. As there are lots of machine learning algorithms that can be used to detect malware. Besides, a lightweight model is required for the malware detection algorithm to maintain its accuracy without sacrificing the performance. As a solution, we propose a classifier model based on machine learning that can detect malware activities. This research aims to study the existing malware classification algorithm's features, apply the existing algorithm, and evaluate the algorithm for malware classification. This algorithm can detect the malware with high accuracy up to 99.3%.  The output of this research will be significantly used in detecting malware attacks that benefit multiple industries including cybersecurity contractors, oil and gas, water, power and energy industries which align with the National Cyber Security Policy (NCSP) which address the risks to the Critical National Information Infrastructure (CNII).