TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Hengkai, Zhang, Zhechang, Jia, Jinyuan, Hu, Hong
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.07536