Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Manjiang, Singh, Priyanka, Li, Xue, Cao, Yang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.23246