Writing

IEEE research on LLM security, and one manuscript under review. This is not a blog.

• Code Poisoning Through Misleading Comments: Jailbreaking Large Language Models via Contextual Deception

  IEEE ICCIT 2025

  A published IEEE paper on comment-based attacks against LLMs.

  • Research Site
  • Dataset (Zenodo)
  • GitHub

• Agentic Artificial Intelligence: A Survey of Architectures, Evolutionary Dynamics, and Governance

  Under review, 2026. Information Processing & Management (Elsevier).

  Survey of agentic architectures, how those systems evolve in practice, and the governance questions that follow from deploying them. Co-authored with EARL collaborators.

I also write at Developer Data.