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

Stereotype Content Model02:16

Stereotype Content Model

13.9K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
13.9K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

38
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
38

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

[Evaluation of palatal bone thickness in adults with normal occlusion for orthodontic miniscrews placement].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2011
Same author

5-Methyl-1-(3-nitro-benz-yl)-1H-1,2,3-triazole-4-carboxylic acid monohydrate.

Acta crystallographica. Section E, Structure reports online·2011
Same author

1-Benzyl-5-methyl-1H-1,2,3-triazole-4-carboxylic acid monohydrate.

Acta crystallographica. Section E, Structure reports online·2011
Same author

1-[(3-Methyl-piperidin-1-yl)(phen-yl)meth-yl]-2-naphthol.

Acta crystallographica. Section E, Structure reports online·2011
Same author

Determination of fumaric and maleic acids with stacking analytes by transient moving chemical reaction boundary method in capillary electrophoresis.

Journal of chromatography. A·2011
Same author

On-road pollutant emission and fuel consumption characteristics of buses in Beijing.

Journal of environmental sciences (China)·2011

相关实验视频

Updated: May 23, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

474

有效的黑子攻击使用替代模型和多个通用对抗性扰动.

Tao Ma1, Hong Zhao2, Ling Tang3

  • 1National University of Defense Technology, Hefei, 230000, China.

Scientific reports
|May 19, 2025
PubMed
概括

本研究介绍了SMPack,这是一个高效的算法,用于在黑盒设置中生成对抗性示例. SMPack利用多重通用对抗性扰乱 (MUAP) 和遗传算法 (GA) 来提高攻击成功率和查询效率.

更多相关视频

Setting Limits on Supersymmetry Using Simplified Models
07:46

Setting Limits on Supersymmetry Using Simplified Models

Published on: November 15, 2013

8.5K
Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

645

相关实验视频

Last Updated: May 23, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

474
Setting Limits on Supersymmetry Using Simplified Models
07:46

Setting Limits on Supersymmetry Using Simplified Models

Published on: November 15, 2013

8.5K
Surrogate Model Development for Digital Experiments in Welding
09:17

Surrogate Model Development for Digital Experiments in Welding

Published on: March 28, 2025

645

科学领域:

  • 深度学习 (Deep Learning) 是一种深度学习.
  • 敌对的机器学习
  • 计算机视觉 计算机视觉

背景情况:

  • 深度学习模型容易受到对抗性示例的影响,特别是在黑子场景中.
  • 现有的黑子攻击在有效性和效率方面扎,通常需要广泛的查询.

研究的目的:

  • 开发一种高效和有效的算法,用于在黑盒设置中生成对抗性示例.
  • 解决当前黑子攻击方法在查询预算和成功率方面的局限性.

主要方法:

  • 研究了多重普遍对抗性扰乱 (MUAP) 的可转移性.
  • 提出了SMPack,这是一个分阶段的算法,集成了MUAP,替代模型和遗传算法 (GA).
  • 在四个数据集 (MNIST,SVHN,CIFAR-10,ImageNet) 上对八个现有算法进行了SMPack的评估.

主要成果:

  • 与现有的黑子方法相比,SMPack展示了优越的攻击成功率 (ASR) 和查询效率.
  • 该算法实现了与白盒攻击方法相比具有竞争力的性能.
  • SMPack有效地克服了黑子约束,并优化了扰动生成.

结论:

  • SMPack提供了一个高效和有效的解决方案,用于黑子对抗性示例生成.
  • 整合MUAP,替代方案和GA优化大大降低了查询预算要求.
  • 在有限知识的场景中,SMPack为产生对抗性干扰提供了一个强大的替代方案.