BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Yi, Sun, Weiyu, Huynh, Tran Ngoc, Song, Dawn, Li, Bo, Jia, Ruoxi
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.17092