Study on Machine Learning Techniques for Botnet Detection

Abstract

This study presents the study of Machine Learning methods applied to the detection of Botnets, compromised computer networks that are controlled by an attacker in order to perform malicious activities such as DDoS attacks, data theft, among others. This work is focused on studying the efficiency of the most used classifiers in previous studies of the area and apply techniques to select the most relevant network characteristics in the task of selecting botnet traffic in a network environment, through a brute-force approach and using the Recursive Feature Elimination algorithm.