ASPECTS OF DETECTING MALICIOUS INSTALLATION FILES USING MACHINE LEARNING ALGORITHMS

This work presents the research of using machine learning methods to detect malicious
installation files, specifically trojan droppers and downloaders, and installers with extraneous
functionality. A comparative analysis of some classification methods of machine learning is presented:
the naive bayes classifier, the random forest and the C4.5 algorithms. The classification
was carried out using the Weka software in accordance with the methods under consideration.
Significant attributes of executable files are defined, which give positive results in the classification
of legitimate installers and trojans