DDoS attack detection and defense in SDN based on machine learning
Tan-Khang Luong, Trung-Dung Tran, Giang-Thanh Le
Abstract
Distributed Denial of Service (DDoS) attack is one of the most dangerous threats in computer networks. Hence, DDoS attack detection is one of the key defense mechanisms. In this paper, we propose a DDoS detection and defense approach in Software Defined Network (SDN) systems based on machine learning (ML) and deep neural network (DNN) models. The combination of ML and DNN classifiers with the centralized factors of SDN can efficiently mitigate the harmful effect of DDoS to the network system. Besides, we conducted two types of attack scenarios, one is from inside and one is from outside of the network system.
Topics & Concepts
Denial-of-service attackComputer scienceApplication layer DDoS attackTrinooSoftware-defined networkingKey (lock)Computer securityArtificial neural networkComputer networkSoftwareArtificial intelligenceBotnetMachine learningOperating systemThe InternetNetwork Security and Intrusion DetectionInternet Traffic Analysis and Secure E-votingSoftware-Defined Networks and 5G