A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Peng, Kuang, Jun, Ma, Dan, Cao, Xuezhi, Xian, Yunsen, Chen, Jiajun, Huang, Shujian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!