Nate Mathews

Nate Mathews

PhD Candidate specializing in the application of machine learning and deep learning techniques to address cybersecurity challenges, particularly in network traffic analysis.

Teaching Generative AI for Cybersecurity: A Project-Based Learning Approach

Published in Journal of The Colloquium for Information Systems Security Education (CISSE), 2025

In this paper, we describe the design and outcomes of an elective course “Generative AI and Cybersecurity” offered in Spring 2024 to MS and advanced BS students. The course employs a project‑based learning framework, featuring three team projects—document generation, AI‑assisted code development, and advanced generative AI applications—that leverage prompt engineering, retrieval‑augmented generation (RAG), and fine‑tuning of large language models. Integrated ethics and legal discussions, complemented by industry guest lectures, foster critical reflection on AI’s societal impact. We adopt an ungrading assessment strategy, where students submit reflective essays and self‑assigned grades guided by structured prompts. A post‑course survey and analysis of student reflections demonstrate significant gains in technical proficiency, ethical awareness, teamwork, and confidence in applying generative AI to real‑world cybersecurity challenges. Our findings highlight the effectiveness of hands‑on, reflective, and ethically grounded approaches in preparing students for emerging AI‑driven security roles.

Recommended citation: Nate Mathews, Christopher Schwartz, Matthew Wright. (2025). “Teaching Generative AI for Cybersecurity: A Project‑Based Learning Approach.” Journal of The Colloquium for Information Systems Security Education, 12(1), 1–10. DOI: 10.53735/cisse.v12i1.211.
Download Paper