Research Blog

Weekly insights from our cybersecurity research journey

62 Vulnerabilities, 26 Projects, 36 Patches: FuzzingBrain's Open Source Security Campaign

How our AI-assisted fuzzing system discovered and helped fix critical zero-day vulnerabilities in widely-used open source software -- from CUPS and Apache Avro to Ghidra and OpenLDAP.

62 Zero-Days 26 Projects 43 Confirmed 36 Patched

Read Full Post →

Recent Posts

October 6, 2025 Architecture

Scaling to 100 VMs: FuzzingBrain's Parallel Architecture

How we coordinate four services across ~100 VMs to run thousands of concurrent jobs and 100K+ LLM requests with robust validation.

Published

September 29, 2025 Technical Deep-dive

LLM-Powered Fuzzing: Our 23-Strategy Arsenal

A practical breakdown of 10 discovery and 13 patching strategies.

Published

September 22, 2025 Live Demo

Claude Code vs AIxCC: $0.26 and 7 Minutes to Find and Fix a Critical Vulnerability

Claude Code finds a libpng overflow, builds a PoC exploit, and ships a clean patch.

Published

September 15, 2025 Research Tools

FuzzingBrain Leaderboard: The First Benchmark for LLM-Powered Cybersecurity

Benchmarking models on POV and patch generation using AIxCC challenges.

Published

September 8, 2025 Competition

DARPA AIxCC Final: Our Key Achievements

Finalist performance highlights: 28 vulnerabilities, 14 patches, 6 zero-days.

Published