Generative AI & Security

Summer research with Dr. Yang Wang exploring how tools like ChatGPT and Gemini transform ethical hacking workflows, from reconnaisance to reporting.

Overview

This project began in the summer of 2024 and continued through the academic year. We investigated the practical impact of generative AI on information security and ethical hacking practice, focusing on both opportunities and risks for professionals and students.

GenAI Security Ethical Hacking Education

Research Focus

  • Analyzed ChatGPT and Gemini in security-relevant tasks.
  • Defined methods for AI jailbreaking, social engineering, and automation of programming/scripting tasks.
  • Mapped GenAI across ethical hacking phases: reconnaisance, scanning, gaining/maintaining access, covering tracks, and reporting.

Methods & Outcomes

  • Experiment design for safe prompt engineering and red-teaming.
  • Creation of reproducible labs for classroom use.
  • Documentation of risks/mitigations (guardrails, verification, logging).

Publication

Y. Wang, K. Beideman, M. McCoey, and M. Jalalitabar, "Empowering Ethical Hacking Education with Generative AIs: A ChatGPT-Infused Curriculum," Proc. 2025 IEEE Integrated STEM Education Conference, pp. 1-7.

Click here to read!

MSCHE 2024 - Poster Presentation

Presented our findings in Center City, Philadelphia. Spoke with 100+ attendees (professionals, faculty, accreditors, and students) about the role of GenAI in security education.

View the poster (PDF)

Continuing Work

I’m continuing personal research on Ethical Hacking and Pen Testing with AI assistance, and plan to present another poster at MSCHE 2025.

Red Team Blue Team Purple Team OffSec DevSecOps LLM Security Prompt Safety

Opportunities & Collaboration

If you're working in areas like red team, blue team, purple team, penetration testing LLM/appsec, secure prompt engineering, or security education - I'd love to connect.

Contact me