Cryptographic inference for large language model via secret sharing

Inference services based on large language models may lead to the leakage of user input hints to the server or proprietary model weights to the user. Cryptographic techniques such as secure multi-party computation and homomorphic encryption provide feasible solutions to the above problems, but they...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	CHENG Ke, XIA Yuheng, DAI Chuanyun, FU Jiaxuan, ZHU Xinghui, SHEN Yulong
Format:	Artigo
Sprog:	Chinês
Udgivet:	Editorial Department of Journal on Communications 2025-06-01
Serier:	Tongxin xuebao
Fag:	privacy-preserving large language model secret sharing secure multi-party computation cryptographic inference
Online adgang:	http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025115/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!