Workshops & Talks
Workshop
Tom Builds, Tom Breaks: Hands-On Attacks and Defenses for Vision-Language Systems
CVPR · 2026-06-03
Workshop
How to Break an AI: Adversarial Attacks, Jailbreaks, and Defenses That Actually Work
BSides NoVa · 2025-10-10
Talk
AI Security 101: A Practical Roadmap from AppSec to LLM Threat Modeling
BSides Harrisburg · 2026-05-28
Workshop
Words As Weapons: Breaking AI and Agents; Then Securing Them
FLAIRS-39 · 2026-05-17
Workshop
Breaking AI: Prompt Injection, Data Exfiltration and Practical Defenses That Work
BSides Tampa · 2026-05-15
The destination
QBTrain
A hands-on platform for learning AI security and AppSec by actually breaking and securing real systems — prompt injection, data exfiltration, agent abuse, and the defenses that hold. Labs you run in the browser, not slides you sit through.
Research & Publications
Conference Paper
EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System
Proceedings of the AAAI Symposium Series · 2025
Conference Paper
Preventing Another Tessa: Modular Safety Middleware for Health-Adjacent AI Assistants
Proceedings of the AAAI Symposium Series · 2025
Conference Paper
AnoGAN for Tabular Data: A Novel Approach to Anomaly Detection
Proceedings of the International Conference on Human-Computer Interaction (HCII 2024) · 2024
Professional Experience
Principal Developer
Automata LLC · Arlington, Virginia· Present
Software Engineer
Automata LLC · Arlington, Virginia· 2026-03
Associate Software Engineer
Antra Inc. · Sterling, Virginia· 2026-03