PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration

Autor: Zeng, Ziqian, Wang, Jianwei, Yang, Junyao, Lu, Zhengdong, Zhuang, Huiping, Chen, Cen

The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers. Existing privacy protection methods

Externí odkaz: http://arxiv.org/abs/2406.01394

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Inverse order based optimization method for task offloading and resource allocation in mobile edge computing

Autor: Yang, Junyao, Wang, Yan, Li, Zijian

Publikováno v: In Applied Soft Computing Journal February 2022 116

Attention based multilayer feature fusion convolutional neural network for unsupervised monocular depth estimation

Autor: Lei, Zeyu, Wang, Yan, Li, Zijian, Yang, Junyao

Publikováno v: In Neurocomputing 29 January 2021 423:343-352

Variable-stiffness optimization of CFRP body panels for body-in-white.

Autor: Lv, Tiantong, Wang, Dengfeng, Du, Xuejing, Yang, Junyao, Chen, Zipeng

Publikováno v: Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering (Sage Publications, Ltd.); May2024, Vol. 238 Issue 6, p1497-1513, 17p