Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Haoyu, Sun, Youran, Cai, Yunfeng, Zhu, Jun, Zhang, Bo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2501.18280