Network Traffic Analysis for DDOS Attack Detection

Abstract

Distributed Denial of Service attacks (DDoS) are one of the most prevalent attacks threatening systems and their security. In this paper, various models to categorize these attacks are presented, analyzed and compared on regards of their effectiveness for DDoS detection. Machine learning (ML) algorithms for classification are used after pre-processing DDoS dataset to classify network traffic. After analyzing the results of Naïve bayes, Decision Tree, Support Vector Machine, and Random Forest classifiers, we conclude that the most accurate results appeared when using the Random Forest classifier.