A Machine Learning Based DDoS Attack Detection Method In SDN Networks

XJTU 2024 CSUC Submission7 Authors

31 Mar 2024 (modified: 03 Apr 2024)XJTU 2024 CSUC SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Software Defined Networking, DDoS attack, Machine learning, Network attack protection, SYN Flood
Abstract: The concept of Software Defined Networking (SDN) represents a modern way to organize computer network as it decouples the control plane from the data plane through network abstraction. However, countering Distributed Denial-of-Service (DDoS) attacks aimed at controllers has become a major issue in SDNs, as the controller responsible for managing network traffic is a sensitive failure point in the entire network architecture. This article mainly introduces a method for extracting traffic packet features in SDN Networks and utilizing machine learning algorithm for their classification. This technology can be used to identify packets in SDNs that are utilized for conducting DDoS attacks to the network and protect the network from failing. In our testing on a simple SDN Network using KDD-CPU99 dataset, this method demonstrated acceptable performance.
Submission Number: 7