Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Che, Zora, Casper, Stephen, Kirk, Robert, Satheesh, Anirudh, Slocum, Stewart, McKinney, Lev E, Gandikota, Rohit, Ewart, Aidan, Rosati, Domenic, Wu, Zichu, Cai, Zikui, Chughtai, Bilal, Gal, Yarin, Huang, Furong, Hadfield-Menell, Dylan
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Similar Items