Features of Detecting Malicious Installation Files Using Machine Learning Algorithms

Abstract

This paper presents a study of the possibility of using machine learning methods to detect malicious installation files related to the type of Trojan installers and downloaders. A comparative analysis of machine learning algorithms applicable for the solution of this problem is provided: the naive Bayes classifier (NBC), random forest, and C4.5 algorithm. Machine learning models are developed using the Weka software. The most significant attributes of installation files of legitimate and Trojan programs are highlighted.