Cover Image

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Draguns, Andis, Gritsevskiy, Andrew, Motwani, Sumeet Ramesh, Rogers-Smith, Charlie, Ladish, Jeffrey, de Witt, Christian Schroeder
Format: Preprint
Published: 2024
Subjects:
Cryptography and Security
Machine Learning
Online Access:
Acceder al recurso
Tags: Add Tag
No Tags, Be the first to tag this record!
Be the first to leave a comment!
You must be logged in first

Similar Items