A Study on the Effect of Feature Selection on Malware Analysis using Machine Learning

Abstract

In this paper, the effect of feature selection in malware detection using machine learning techniques is studied. We employ supervised and unsupervised machine learning algorithms with and without feature selection. These include both classification and clustering algorithms. The algorithms are compared for effectiveness and efficiency using their predictive accuracy, among others, as performance metric. From the studies, we observe that the best detection rate was attained for supervised learning with feature selection. The supervised learning algorithm used was Multilayer Perceptron (MLP) algorithm. The analysis also reveals that our system can detect viruses from varying sources.