Graduate Degree Type
School of Computing and Information Systems
In recent years, software defined networking (SDN) has gained popularity as a novel approach towards network management and architecture. Compared to traditional network architectures, this software-based approach offers greater flexibility, programmability, and automation. However, despite the advantages of this system, there still remains the possibility that it could be compromised. As we continue to explore new approaches to network management, we must also develop new ways of protecting those systems from threats. Throughout this paper, I will describe and test a network intrusion detection system (NIDS), and how it can be implemented within a software defined network. This system will utilize machine learning techniques to discern between normal and malicious network traffic. The datasets that will be used for training and testing these machine learning methods include the UNR-IDD dataset, and the NSL-KDD dataset. The UNR-IDD dataset was created by researchers at the University of Nevada, Reno, and is intended to provide a wide range of samples and scenarios for machine learning-based intrusion detection systems. The NSL-KDD dataset is a newer version of the KDD '99 dataset, and is used as an effective benchmark for helping researchers compare various intrusion detection methods. Feature selection techniques will be performed during the testing phase to ensure the best features are used when performing analysis. In doing so, we’ll be able to extract the best results possible from the experiments to determine the accuracy and effectiveness of the IDS.
Rodriguez, Jacob S., "Intrusion Detection: Machine Learning Techniques for Software Defined Networks" (2023). Masters Theses. 1099.