Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Halawi, Danny, Wei, Alexander, Wallace, Eric, Wang, Tony T., Haghtalab, Nika, Steinhardt, Jacob
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence 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/2406.20053