StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Huawei, Jiang, Xinqi, Yang, Sen, Ji, Shouling, Wu, Yingcai, Deng, Dazhen
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.04740