Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Guanzhong, Qin, Zhenghan, Yang, Mingxin, Zhou, Yajie, Fan, Tao, Du, Tianyu, Xu, Zenglin
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security K.6.5
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2409.00960