DEFENSE MECHANISM FOR DDOS ATTACK THROUGH MACHINE LEARNING

Sujay Apale, Rupesh Kamble, Manoj Ghodekar, Hitesh Nemade

Abstract: There is a huge advancement in Computer networking in the past decade. But with the advancement, the threats to the computer networks are also increased. Today one of the biggest threats to the computer networks is the Distributed Denial of Service (DDoS) flooding attack. This paper emphasizes the application layer DDoS flooding attacks because these (layer seven) attacks are growing rapidly and becoming more severe problem. Many researchers used machine-learning techniques for intrusion detection, but some shows poor detection and some methods take more training time. From a survey, it is found that Naïve Bayes (NB) algorithm provides faster learning/training speed than other machine learning algorithms. Also it has more accuracy in classification and detection of attack. So we are proposing a network intrusion detection system (IDS) which uses a machine learning approach with the help of NB algorithm

Keywords: DDoS (Distributed Denial of Service) flooding attack, Machine Learning, Naïve Bayes, Network Intrusion Detection

DOI: https://doi.org/10.15623/ijret.2014.0310045