Developing a Testing Framework for Intrusion Detection Algorithms Using Software Defined Networking

• Main Authors: Suba, Anton Miguel, Bautista, Kurt Vincent, Ledesma, Julio Carlos Tomas, Yu, William Emmanuel S
• Format: text
• Published: Archīum Ateneo 2018
• Subjects: Intrusion detection system; Machine learning; Mininet; Software defined networking; Testing framework; Computer Sciences; Databases and Information Systems
• Online Access: https://archium.ateneo.edu/discs-faculty-pubs/301; https://link.springer.com/chapter/10.1007/978-981-13-1056-0_32
• Institution: Ateneo De Manila University

Software defined networking (SDN) is an emerging type of network technology that aims to make the network flexible and adaptable. This paper presents a study that explores the creation of a testing framework for intrusion detection systems (IDS) created using SDN. IDSes created using SDN have a distinct flexibility and configurability that current network security do not have. While there have been a number of network security software created using SDN, there is a lack of a way to easily test these software and show results. This study aimed to create a tool that would test these systems and allow for easy generation of network topologies, training of machine learning models, and swapping of test scripts. The methodology entails the creation of the testing framework to test IDSes in an intuitive and user-friendly way, then using a machine learning IDS created using SDN to test the effectiveness of the testing framework. The results of the experiment show that the framework was able to successfully test an IDS, and give accurate results.