OAIC 2026 / Full talk / 30:11

Vibe Fuzzing

Name: Vibe Fuzzing: Building an AI-Guided Fuzzing Engine from Scratch
Uploaded: 2026-10-23
Duration: 30 min 11 s
Description: Sam Lovejoy of IBM X-Force Offensive Research explains how VF3 combines graph-based input generation, state-aware fuzzing, and LLM guidance to target code and patches while keeping the fuzzing loop fast. He covers Markov-chain grammars, program state, model context, performance, and cost, followed by a live demonstration and audience Q&A.

Building an AI-Guided Fuzzing Engine from Scratch

Sam Lovejoy · IBM X-Force Offensive Research

About the talk

Sam Lovejoy of IBM X-Force Offensive Research explains how VF3 combines graph-based input generation, state-aware fuzzing, and LLM guidance to target code and patches while keeping the fuzzing loop fast. He covers Markov-chain grammars, program state, model context, performance, and cost, followed by a live demonstration and audience Q&A.

Recorded at Offensive AI Con 2026. Includes updated slides and audience Q&A. The live demo section retains the speaker camera and original explanation.

Watch on YouTube ↗

The next wave of offensive AI