dallas@tulsa: ~/resume
dallas@tulsa:~/resume$ cat dissertation.md
Alignment Learning Models — Toward a Formal Framework for Detecting Behavioral Misalignment in AI Agents
advisor: John Hale (Chair) · committee: Tyler Moore, Brett McKinney, Roger Wainwright
Trains structured-trajectory models (extending Decision Transformers) on agent action sequences encoded under a 5-element ontology (Agents, Assets, Aims, Actions, Ambits) to detect covert objectives — prompt injection, jailbreak-induced policy drift, and fine-tuned hidden goals — at the trajectory level rather than the language level.
dallas@tulsa:~/resume$ pubs
publications
First author · ICISSP 2026 · 2026
Contributing author · PCAST · U.S. Dept of Energy · 2021
dallas@tulsa:~/resume$ talks
talks
2026-04 · BSidesOK · Tulsa, OK
Live talk delivered through a custom local FastAPI + reveal.js stack with a co-presenting Claude Code session that listens to the room via Whisper.cpp and edits the slide deck in real time.