Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deng, Guilin, Chen, Silong, Luo, Yuchuan, Liu, Yi, Wang, Songlei, Cai, Zhiping, Liu, Lin, Jia, Xiaohua, Fu, Shaojing
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.21197