PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Winning the AIxCC Qualification Round

theori.io | research | #ctf | #llm | #darpa | #cyber-reasoning-system | #aixcc | #roboduck
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Theori’s RoboDuck cyber reasoning system took first place in DARPA’s AIxCC qualification round, earning the most achievements and unique bug classes and securing $2M plus a 2025 finals spot.
Published
Collected

Related coverage

research · theori.io
Building Effective LLM Agents | AI Cyber Challenge
Lessons from building LLM agents for DARPA’s AI Cyber Challenge: decomposing tasks, curating toolsets and adapting to models, applied to vulnerability detection, PoV generation and patching.
research · theori.io
AI Cyber Challenge and Theori's RoboDuck
A look at DARPA’s AI Cyber Challenge and Theori’s open-sourced RoboDuck cyber reasoning system, including its LLM-first design and a pipeline producing POVs without fuzzing or symbolic execution.
blog · blog.trailofbits.com
DARPA awards $1 million to Trail of Bits for AI Cyber Challenge
Trail of Bits is one of seven teams selected for DARPA's AI Cyber Challenge small business track, receiving $1 million to build a Cyber Reasoning System that finds and fixes software vulnerabilities.
blog · blog.trailofbits.com
Our thoughts on AIxCC’s competition format
Trail of Bits dissects DARPA's AIxCC format: automated systems must find and patch vulnerabilities in critical software, with concerns flagged on challenge construction, PoU granularity, and scoring.
blog · blog.trailofbits.com
DARPA’s AI Cyber Challenge: We’re In!
Trail of Bits announces it will compete in DARPA's AI Cyber Challenge (AIxCC), fielding an AI/ML-driven Cyber Reasoning System built by its software security and AI experts.
blog · blog.trailofbits.com
AIxCC finals: Tale of the tape
Interviews with the seven AIxCC finalists reveal diverse approaches, from AI-first discovery to enhanced fuzzing, showing multiple viable paths to AI-driven vulnerability detection and patching.
Back