Date of Defense

4-23-2025

Date of Graduation

4-2025

Department

Business Information Systems

First Advisor

Ting-Yu (Kevin) Mu

Second Advisor

Alan Rea

Keywords

Generative AI, GenAI, SDN, artificial intelligence, machine learning, cybersecurity, network security, anomaly, GAN, generative adversarial network

Abstract

This paper aims to explore various approaches to using generative artificial intelligence (GenAI) to improve network security in software-defined networking. While software-defined networks provide a more programmable infrastructure, they are not immune to network security threats. Through a combination of Software-Defined Networking (SDN) technologies and generative AI, it is possible to facilitate improved SDN security approaches that promise enhanced network efficiency and protection. Among these approaches, generative adversarial networks (GAN) based models can be employed to generate adversarial traffic samples to train the proposed AI engines proven to be effective in detecting malicious network traffic. Additionally, generative artificial intelligence can be used to perform AI attack simulations and enhance routing optimization, both of which have implications in improving network security.

Access Setting

Honors Thesis-Open Access

Presentation .pdf (220 kB)
Defense Presentation

Share

COinS