PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Coalson, Zachary, Woo, Jeonghyun, Lin, Chris S., Qu, Joyce, Sun, Yu, Chen, Shiyang, Yang, Lishan, Saileshwar, Gururaj, Nair, Prashant, Fang, Bo, Hong, Sanghyun
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2412.07192