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

相关概念视频

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

441
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
441
Retrieval01:12

Retrieval

484
Retrieval is the process of getting information out of memory storage and back into conscious awareness. This ability is essential for daily tasks like brushing hair and teeth, driving to work, and performing job duties. Retrieval occurs in three ways: recall, recognition, and relearning.
Recall involves accessing information without cues, such as during an essay test, where individuals must retrieve facts and concepts from memory unaided. Another example is remembering the name of a colleague...
484

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

A reconfigurable MTM-EMBG MIMO antenna array with solar panel integration for sustainable 5G networks.

Scientific reports·2026
Same author

Early lumbar drainage plus intrathecal urokinase in severe aneurysmal subarachnoid hemorrhage: the LD-ITUK randomized controlled trial protocol.

Trials·2026
Same author

Analysis of the characteristics of rumen microorganisms and their metabolites and plasma metabolites in crossbred beef cattle at different stages.

Veterinary research communications·2026
Same author

Medical management and revascularization for asymptomatic carotid stenosis: a meta-analysis of randomized controlled trials.

Journal of neurology·2026
Same author

Construction of the ceRNA Regulatory Network Associated with Milk Fat Metabolism.

Animals : an open access journal from MDPI·2026
Same author

Integrating multi-omics to characterize the dynamics of rumen microorganisms and metabolites in Angus cattle at different growth stages.

Research in veterinary science·2026

相关实验视频

Updated: Feb 26, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.5K

一个保护隐私的多用户检索系统,用于多模式的人工智能.

Yifang Gao1, Wei Luo2, Chuanchuan Wang3

  • 1School of Electrical and Electronic Engineering, Universiti Sains Malaysia, 14300, Penang, Malaysia.

Scientific reports
|February 24, 2026
PubMed
概括

本研究介绍了PMIRS,这是使用大型语言模型 (LLM) 进行保护隐私的多式联络检索的安全系统. 通过模糊,加密和联合学习,PMIRS提高了数据安全性,实现了高精度和低延迟.

关键词:
交叉模式的检索检索多模式深度学习 (deep learning) 是一种多模式深度学习.多式联运系统是多式联运系统.保护隐私的AI保护隐私可搜索的加密技术可以进行搜索.

更多相关视频

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.9K

相关实验视频

Last Updated: Feb 26, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.5K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.9K

科学领域:

  • 人工智能的人工智能
  • 计算机安全 计算机安全
  • 信息检索 信息检索

背景情况:

  • 大型语言模型 (LLM) 对人工智能至关重要,但在多用户云环境中可能会带来隐私风险.
  • 安全和私密的多式联运数据检索是一个重大挑战.

研究的目的:

  • 介绍PMIRS,这是一个新的系统,用于安全,以隐私为中心的多式联络图像和文本数据的检索.
  • 为了使数据安全地传输到基于云的LLM,同时减轻隐私风险.

主要方法:

  • PMIRS使用模糊化技术,加密推断 (AES-CBC) 和联合学习来微调基于CLIP的模型.
  • 迪菲-赫尔曼算法确保了多用户设置中的安全密钥管理.
  • 查询嵌入被通过区块智能投影模糊并被加密.

主要成果:

  • 在一个定制的ImageNet数据集上,PMIRS实现了高达0.92的F1分数和超过0.90的精度.
  • 检索延迟始终低于180毫秒.
  • 与CLIP基线相比,PMIRS的平均F1得分提高了7.67%,保持了精度.

结论:

  • PMIRS提供了一种实用的解决方案,用于安全,高效和保护隐私的多式联运检索.
  • 该系统在医疗成像,客户服务和企业数据管理等领域具有潜在的应用,这些应用在GDPR和HIPAA等法规下进行.