Publication Date
Spring 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Genya Ishigaki
Second Advisor
Fabio Di Troia
Third Advisor
Sayma Akther
Keywords
Network Intrusion Detection, Distributed Denial of Service, Ensemble Learning, Meta-Learner, Mininet, Ryu Controller.
Abstract
In response to the security threats posed by Distributed Denial of Service (DDoS) attacks, this paper presents an intrusion detection framework with a high-accuracy multi-class classification model. In addition to detecting the existence of DDoS attacks, our framework aims to identify the type of attack (e.g., protocol or message type) so that the system can select the most appropriate countermeasure against the DDoS type. We leverage a meta-learner to build an ensemble model of multiple machine learning models such as LSTM, RF, and KNN to enhance detection and classification accuracy. Tested on the CIC-DDoS 2019 dataset, the proposed model achieves 96% accuracy in the type identification task, while a simple combination of existing detection classifiers only achieves 92% accuracy in the same type identification. To demonstrate a practical implementation of the DDoS classification model, we integrated the model with the Ryu SDN controller running on a Mininet network testbed, which emulates different types of DDoS attacks and benign traffic. The integrated ensemble model achieved 93% accuracy in identifying the DDoS types in the testbed experiment.
Recommended Citation
Indrakumar, Ankith, "Ensemble Model with Meta-Learning for DDoS Attack Classification in SDN" (2024). Master's Projects. 1400.
https://scholarworks.sjsu.edu/etd_projects/1400
