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

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

5.2K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
5.2K

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

Network analysis of depression, anxiety, and NSSI symptoms in adolescents: a clinical sample study.

BMC psychiatry·2026
Same author

Artifact-suppression-based point-cloud holography for multi-depth scenes.

Optics express·2026
Same author

ABIGX: A Unified Framework for eXplainable Fault Detection and Classification.

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

The impact of hospital pharmacists' psychological contracts on medication adherence management: The mediating role of job burnout.

PloS one·2026
Same author

Electroacupuncture-induced Changes in Motor Protein Pathways in Postpartum Stress Urinary Incontinence.

Journal of visualized experiments : JoVE·2026
Same author

Radical Synergy Between Initiating and Inhibitor Species Enables Kinetically Controlled Holographic Polymerization.

Small (Weinheim an der Bergstrasse, Germany)·2026

相关实验视频

Updated: May 23, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

数据ID提取网络用于无监督的类和分类器免费检测对抗性示例.

Xiangyin Kong, Xiaoyu Jiang, Zhihuan Song

    IEEE transactions on pattern analysis and machine intelligence
    |May 21, 2025
    PubMed
    概括

    这项研究引入了一种新的无监督方法来检测对抗性示例,这是操纵的输入,欺骗深度神经网络 (DNN). 该方法有效地识别恶意样本,而不需要先前了解攻击类型或数据类别.

    科学领域:

    • 人工智能的人工智能
    • 机器学习 机器学习
    • 计算机视觉 计算机视觉

    背景情况:

    • 深度神经网络 (DNN) 是强大的,但易受对抗的例子.
    • 敌对攻击对DNN的可靠性构成重大威胁.
    • 现有的检测方法通常需要标记数据或对攻击的了解.

    研究的目的:

    • 提出一种不受监督,没有类别和分类器的对抗性检测方法.
    • 开发一个强大的探测器,不需要对对抗示例,类或原始分类器的先验知识.
    • 加强深度学习模型的安全性和可靠性,以防止对手操纵.

    主要方法:

    • 开发了一个利用样本结构信息的对抗检测器,捕获残余信息和变量智能的结构关系.
    • 引入了一个新的属性,数据标识 (ID),将提取的剩余和结构信息结合起来,用于对抗样本的识别.
    • 训练检测器只使用未标记的清洁数据,使其广泛适用.

    主要成果:

    • 拟议的方法在检测CIFAR-10和ImageNet数据集的对抗性攻击方面取得了最先进的性能.
    • 与现有的对抗性检测技术相比,展示了优越的检测能力.
    • 可视化实验证实了结构信息在识别对抗性示例方面的有效性.

    更多相关视频

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    449
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K

    相关实验视频

    Last Updated: May 23, 2025

    Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
    08:20

    Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

    Published on: October 27, 2023

    1.3K
    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    449
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K

    结论:

    • 无监督,无类和分类器的方法为减轻对抗性威胁提供了一个非常有效的策略.
    • 数据身份属性通过分析它们的结构性质,成功地区分了对抗性示例.
    • 这种方法为构建更有弹性的深度学习系统提供了一个有希望的方向.