IBM X-Force's Vibe Fuzzing Talk: LLM-Guided Fuzzing with Graph Inputs and Program State
dyn___ · x · 2026-10-24
At OAIC 2026, Sam Lovejoy of IBM X-Force Offensive Research presented "Vibe Fuzzing," exploring how graph-based inputs, program state, and LLM guidance combine in an AI-guided fuzzing engine — and the tradeoffs behind the design. The full talk video is available.
More from Safety
- PHP2Shell, GitLab RCE, eMudhra CA failures in one week: why patching can't keep up — WeldPond · 2026-10-24
- Inside the Artificial Analysis Cyber Index: three real-repo vuln-fixing evals, DeepSeek on top — ArtificialAnlys · 2026-10-24
- DeepSeek V4.1 Flash 1017 takes #1 open-model spot on Cyber Index, CyberGym up 53 points — ArtificialAnlys · 2026-10-24
- Moonshot lays out open-weight principles: never ship weights that extend the cyber frontier — teortaxesTex · 2026-10-24
- Honeypot for agents: a flag.txt prompt injection that tricks bots into patching their own entry and disconnecting — basedjensen · 2026-10-24
- Nathan Lambert: Kimi K3.1 Pro looks like the strongest open-weight model, with deliberate cyber pacing — natolambert · 2026-10-24