AI security, red teaming, maldev, strategist
- Strategist and Community Manager at Gray Swan AI
- Wins in AI red teaming competitions, Feet Feud winner at DEF CON 33
- Co-author of a 2025 agent red teaming paper on arXiv
- Work referenced in OpenAI system cards
- Building two indie games and a red team tool aimed at a DEF CON 34 talk
- Focused on agent security, evaluation, and maldev
- Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition (2025)
arXiv: https://arxiv.org/abs/2507.20526
Languages: Elixir, Python, TypeScript/JavaScript, Go, C, PowerShell, Bash
Frameworks: Phoenix, React, Next.js, HTMX, Tailwind
Security: Red team ops, LLM and agent adversarial testing, evaluation design, threat modeling
Tooling: Docker, Nmap, Burp, Wireshark, GitHub Actions, Azure
- Gray Swan Arena profile and leaderboards: https://app.grayswan.ai/arena
- OpenAI system cards that reference the arena:
- o1 System Card
https://openai.com/index/openai-o1-system-card/ - o3-mini System Card
https://cdn.openai.com/o3-mini-system-card-feb10.pdf
- o1 System Card