DrDoS DNS Attack Detection Using Machine Learning Algorithms

Distributed Denial of Service (DDoS) attacks are one of the biggest challenges that analysts and researchers face today. Among many, DDoS attack based on the traffic reflection and amplification named Distributed Reflection Denial of Service attack (DrDos attack) still is a powerful threat for computer networks. In DrDos attacks, the victim bombarded by reflected response packets from legitimate hosts, and thus it is difficult to distinguish attack packets from legitimate packets. In this paper,various machine learning models such as Naïve Bayes, KNN, Random Forest and SVM with the state-of-the-art CICDDoS۲۰۱۹ dataset is used for efficient detection of DrDos DNS attacks. The obtained results show better accuracies for the implemented algorithms. It has been delineated that for RF method, ۹۹.۹۹% accuracy which is better in comparison to other works.

Keywords:

Accuracy , Amplification and Reflection Attacks , DrDos DNS Attacks , Machine Learning Methods