FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Meerza, Syed Irfan Ali, Wang, Feiyi, Liu, Jian
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.06297