PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mangaokar, Neal, Hooda, Ashish, Choi, Jihye, Chandrashekaran, Shreyas, Fawaz, Kassem, Jha, Somesh, Prakash, Atul
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2402.15911