As a senior cybersecurity researcher at NIST's Center for AI Standards and Innovation (CAISI), I lead a research team tracking the cyber offense capabilities of AI systems through pre- and post-deployment model evaluations. I also support a team attacking AI systems to discover how these systems could be exploited by nefarious actors. Through close partnerships with leading AI labs and other U.S. government agencies, my work advances our understanding of AI's national security implications and strengthens the resilience of this critical technology.

Previously, I spent a decade at MIT Lincoln Laboratory in the Cyber System Assessments Group, where I led a research team at the intersection of dynamic program analysis, firmware security, and vulnerability discovery. In that role, I helped define the field of firmware rehosting, developed open-source tools, and applied them to evaluate the security of critical systems. Along the way, I developed award-winning tools and techniques for evaluating vulnerability discovery tools, reverse engineering, and software exploitation. My background in systems security and cyber assessments now shapes how I approach AI.

I earned my PhD in Computer Science from Northeastern University and BS from Rensselaer Polytechnic Institute, where I was an active member of RPISEC and its cyber capture the flag (CTF) team. I'm also passionate about cybersecurity education, having developed courses for universities, government agencies, and private companies. The materials from my System Security with Dynamic Program Analysis course are publicly available.

News

2025.09
OpenAI released a blog post describing my discovery of a "sophisticated exploit chain combining traditional software vulnerabilities with AI vulnerabilities" in ChatGPT Agent.
2024.11
Joined NIST's Center for AI Standards and Innovation to lead research on AI cyber capabilities in collaboration with frontier AI labs.
2024.08
Presented "A Reverse Engineer's Guide to Mechanistic Interpretability" at DEF CON, describing how we can understand the internals of Large Language Models and how it differs from software reverse engineering.
2020.09
LAVA awarded R&D100 Award for enabling rigorous, large-scale, and repeatable evaluation of automated vulnerability discovery tools.
2017.07
Led Lab RATs team to a 10th place finish at DEF CON CTF finals, as covered by the MIT News.
2016.12
Discovered 10 CVEs in a McAfee antivirus product, as covered by The Register and ZDNet.

Select Projects and Publications

Invited Talks

Honors and Awards

R&D100 Award
2020.09
LAVA was awarded an R&D100 award for its impact advancing the state of the art in vulnerability discovery and enabling rigorous, large-scale evaluation of automated security tools.
MIT Lincoln Scholar Award
2019.09
Selected to receive special funding through a competitive process to pursue advanced research in cybersecurity and dynamic program analysis.
MIT Lincoln Laboratory Team Award
2017.06
Recognized for outstanding technical achievement in advancing cybersecurity research and tooling development.

Disclaimer

This is a personal website. The views expressed here are my own and do not necessarily represent the views of my employer or any other organization.