AI RESEARCH
When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output
arXiv CS.AI
•
ArXi:2503.24191v3 Announce Type: replace-cross Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (LLMs) increasingly serve as tooling platforms through structured output APIs, but the grammar-guided decoding that powers this feature opens a critical control-plane attack surface orthogonal to traditional data-plane vulnerabilities. We