When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Shuoming, Zhao, Jiacheng, Dong, Hanyuan, Xu, Ruiyuan, Li, Zhicheng, Zhang, Yangyu, Li, Shuaijiang, Wen, Yuan, Xia, Chunwei, Wang, Zheng, Feng, Xiaobing, Cui, Huimin
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.24191