Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jul 5, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

585

SecBERT:基于预训练的保护隐私的神经网络推断系统.

Hai Huang1, Yongjian Wang1

  • 1Computer School, Zhejiang Sci-Tech University, Hangzhou, 310018, China.

Neural networks : the official journal of the International Neural Network Society
|January 25, 2024
PubMed
概括
此摘要是机器生成的。

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Glass stabilized ultra-stable dual-emitting Mn-doped cesium lead halide perovskite quantum dots for cryogenic temperature sensing.

Nanoscale·2019
Same author

Simultaneous Tailoring of Dual-Phase Fluoride Precipitation and Dopant Distribution in Glass to Control Upconverting Luminescence.

ACS applied materials & interfaces·2019
Same author

<i>Nkx2-5</i> defines a subpopulation of pacemaker cells and is essential for the physiological function of the sinoatrial node in mice.

Development (Cambridge, England)·2019
Same author

Process Analysis of Anaerobic Fermentation Exposure to Metal Mixtures.

International journal of environmental research and public health·2019
Same author

Surface-to-Bulk Redox Coupling through Thermally Driven Li Redistribution in Li- and Mn-Rich Layered Cathode Materials.

Journal of the American Chemical Society·2019
Same author

Chlorine-additive-promoted incorporation of Mn<sup>2+</sup> dopants into CsPbCl<sub>3</sub> perovskite nanocrystals.

Nanoscale·2019

本研究介绍了SecBERT,这是一种使用BERT进行神经网络推理的新型隐私保护方法. 它可以在客户端和两个服务器之间实现安全的自然语言处理任务,而不会泄露数据.

科学领域:

  • 计算机科学 计算机科学
  • 密码学 密码学 密码学 密码学
  • 人工智能的人工智能

背景情况:

  • 像BERT这样的预先训练有素的模型在自然语言处理 (NLP) 中表现出色.
  • 现有的方法往往缺乏在推理过程中对敏感数据的强有力的隐私保障.
  • 安全计算对于保护隐私的人工智能应用程序至关重要.

研究的目的:

  • 为预先训练的神经网络开发一种加密安全,保护隐私的推理协议.
  • 为了使资源有限的客户端能够利用强大的服务器进行NLP任务,而不会影响数据隐私.
  • 为BERT必不可少的非线性功能设计安全的子协议.

主要方法:

  • 使用添加式秘密共享来实现双服务器框架.
  • 为BERT内部的非线性函数设计安全的子协议.
  • 开发了SecBERT,一种新的隐私保护推理协议.

主要成果:

  • SecBERT提供了第一个加密安全协议,用于保护隐私的预训练神经网络推理.
  • 通过理论分析和实验证明了SecBERT协议的安全性,效率和准确性.
  • 为常见的非线性函数开发了可重复使用的安全子协议.
关键词:
贝尔特 (BERT) 公司神经网络推断推断的神经网络推断.预先训练的模型模型.保护隐私的计算可以保护隐私.分享秘密分享 秘密分享

更多相关视频

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents
09:13

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

14.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

相关实验视频

Last Updated: Jul 5, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

585
A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents
09:13

A Fully Automated and Highly Versatile System for Testing Multi-cognitive Functions and Recording Neuronal Activities in Rodents

Published on: May 3, 2012

14.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

结论:

  • SecBERT为保护隐私的NLP推理提供了一个可行的解决方案.
  • 拟议的子协议在BERT之外有潜在的应用.
  • 这项工作通过对敏感数据进行私有计算来推进安全的人工智能.