Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kaunismaa, Jackson, Griffin, Avery, Hughes, John, Knight, Christina Q., Sharma, Mrinank, Jones, Erik
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.13528