Malware Mitigation Through Detection Using Support Vector Machine and Random Forest Algorithm

Abstract

Due to the ever-growing threat of malware application, diverse malware detection mechanism has been developed by researchers. Malware detection relates to the procedure of finding malware on a host device or determining whether a particular program is malicious or benign. An instance of a malware detection mechanism is an anti-malware program designed to automatically identify malicious programs from the benign program to prevent damage to the host system. The methodology used incorporated cutting-edge detection techniques to provide an effective solution to the problem of malicious programs. This study applied a support vector machine and random forest algorithm on malware detection using a dataset obtained from the Kaggle machine learning repository webpage. In an approach to provide a feasible solution, this study structured three methodical approaches that encompass data filtering techniques referred to as preprocessing and the utilization of the correlation metric to select the most relevant features in the first phase. The second approach involves the application of the filtered and selected dataset attributes and tuples to the adapted machine learning models in particular the random forest algorithm and the support vector machine. The final phase as an approach covers the evaluation of the derived model performance using metrics such as precision, accuracy score, and, f1_score. From the statistical result from the two models concerning the evaluation metrics also, it can be deduced that the random forest classifier performs more effectively in the detection of malicious malware from the dataset sourced from the Kaggle machine learning repository.