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

Parallel Processing01:20

Parallel Processing

150
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
150

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

OmniCharacter++: Towards Comprehensive Benchmark for Realistic Role-Playing Agents.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

SeMv-3D: Toward Concurrency of Semantic and Multi-View Consistency in General Text-to-3D Generation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Distribution-to-Points Matching for Image Text Retrieval.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Generalizable Egocentric Task Verification via Cross-Modal Hybrid Hypergraph Matching.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Reliable Few-Shot Learning Under Dual Noises.

IEEE transactions on pattern analysis and machine intelligence·2025

相关实验视频

Updated: Jun 29, 2025

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

19.9K

BadCM:对跨模式学习的隐形后门攻击

Zheng Zhang, Xu Yuan, Lei Zhu

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
    |March 26, 2024
    PubMed
    概括

    这项研究介绍了BadCM,BadCM是一种用于跨模式学习中的隐形后门攻击的新框架. 坏CM有效地针对模态不变组件,增强隐形性和在各种应用中进行概括.

    科学领域:

    • 人工智能的人工智能
    • 机器学习安全 机器学习安全
    • 跨模式学习跨模式学习

    背景情况:

    • 单模式后门攻击得到了很好的研究,但跨模式攻击缺乏概括性和隐形性.
    • 现有的交叉模式攻击往往继承了单模式视觉攻击,限制了它们的有效性.
    • 不易察觉的触发器样本对于实际的真实世界攻击至关重要.

    研究的目的:

    • 为跨模式学习提出一个通用的隐形后门框架.
    • 解决现有的跨模式后门攻击在通用化和隐蔽性方面存在的局限性.
    • 开发一个统一的框架,能够处理各种跨模式攻击场景.

    主要方法:

    • 引入了一种新的双边后门方法.
    • 开发了一种跨模式采矿方案,以确定用于触发器注入的模式不变组件.
    • 设计了针对视觉和语言数据的模式特定生成器,以提高触发器隐形性.
    • 适应了图像-文本交叉模式模型的框架.

    主要成果:

    • 证明了BadCM框架在跨模式检索和视觉问题答案 (VQA) 上的有效性和通用性.
    • 展示了BadCM逃避现有的后门防御的能力.
    • 在有毒样本中通过隐藏模态不变区域中的明确触发器来实现高隐蔽性.

    更多相关视频

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    329
    Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
    08:05

    Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

    Published on: June 30, 2020

    7.5K

    相关实验视频

    Last Updated: Jun 29, 2025

    Cross-Modal Multivariate Pattern Analysis
    13:51

    Cross-Modal Multivariate Pattern Analysis

    Published on: November 9, 2011

    19.9K
    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss
    07:12

    Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

    Published on: April 11, 2025

    329
    Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
    08:05

    Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

    Published on: June 30, 2020

    7.5K

    结论:

    • BadCM是第一个隐形的后门方法,旨在在统一的框架内进行多种多样化的跨模式攻击.
    • 与现有方法相比,拟议的方法提供了更好的概括性和隐蔽性.
    • 在理解和减轻跨模式学习漏洞方面,BadCM取得了重大进展.