Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Yu, Zhang, Qizhi, Ruan, Wenqiang, Zhang, Daode, Hong, Jue, Wu, Ye, Xia, Hanning, Mao, Yunlong, Zhong, Sheng
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.01499