Research.

Papers from the team building autonomous offensive security. How we find vulnerabilities, how we prove them, and what we learn along the way.

Look Here, Then Decide

Small Decision Models in a Harness Find Memory-Safety Vulnerabilities at Scale on Commodity GPUs

Most AI vulnerability research relies on very large, expensive models reasoning through code one file at a time. We asked a different question: can a small, fast model help find real vulnerabilities at scale, if the system around it is designed well? The answer was yes. A model small enough to run on a desktop computer, guided by tools that decide where to look, helped search more than 4,000 open source projects, and the campaign confirmed 187 memory-safety findings.

Tim De WachterKyryl VolkovMyrto Eleftheria GkogkouMathieu Huysman12 Nov 2026arXiv
Vulnerability researchDecision modelsMemory safetyOpen sourceC and C++

More research coming soon.

More from the team on the blog

How we disclose

Request a proposal

Tell us what you ship. Our engineers scope it, and you get a custom proposal within five days.

Tell us the scopeProposal in five daysNo commitment