SecureLLM: Using Compositionality to Build Provably Secure Language Models for Private, Sensitive, and Secret Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Alabdulkareem, Abdulrahman, Arnold, Christian M, Lee, Yerim, Feenstra, Pieter M, Katz, Boris, Barbu, Andrei
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2405.09805