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

Region of Convergence01:17

Region of Convergence

887
The z-transform is a powerful mathematical tool used in the analysis of discrete-time signals and systems. It is a crucial tool in the analysis of discrete-time systems, but its convergence is limited to specific values of the complex variable z. This range of values, known as the Region of Convergence (ROC), is fundamental in determining the behavior and stability of a system or signal. The ROC defines the region in the complex plane where the z-transform converges, which can take various...
887
Anatomy of the Brain: Major Regions01:20

Anatomy of the Brain: Major Regions

9.8K
The brain is the most complex organ in the human body. It consists of four main parts: the cerebrum, diencephalon, cerebellum, and brainstem.
The cerebrum is the largest section of the brain and divides into left and right hemispheres, separated by a deep fissure. The cerebral outer layer of grey matter — the cerebral cortex — comprises elevations called gyri and shallow groves called sulci. The inner portion of white matter includes long nerve fibers known as axons, which connect...
9.8K

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

Dual prototypes for adaptive pre-trained model in class-incremental learning.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

Supervised contrastive learning with prototype distillation for data incremental learning.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Embedding Space Allocation with Angle-Norm Joint Classifiers for few-shot class-incremental learning.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

CS-QCFS: Bridging the performance gap in ultra-low latency spiking neural networks.

Neural networks : the official journal of the International Neural Network Society·2025
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
查看所有相关文章

相关实验视频

Updated: Jan 18, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.4K

区域导向攻击对分段的任何东西模型.

Xiaoliang Liu1, Furao Shen2, Jian Zhao3

  • 1School of Information Engineering, Wenzhou Business College, China.

Neural networks : the official journal of the International Neural Network Society
|September 8, 2025
PubMed
概括
此摘要是机器生成的。

分段任何模型 (SAM) 容易受到对抗性攻击. 一个新的区域引导攻击 (RGA) 通过针对区域有效地操纵图像细分,导致SAM输出中的错误.

关键词:
敌对的攻击是敌对的攻击.一个黑盒子.干扰 干扰 干扰 干扰以地区为导向的地区指导.分段任何模型模型.

更多相关视频

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.3K
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.5K

相关实验视频

Last Updated: Jan 18, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.4K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.3K
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.5K

科学领域:

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

背景情况:

  • 细分任何模型 (SAM) 是一个领先的图像细分工具,对自动驾驶和医学成像至关重要.
  • SAM容易受到对抗性攻击,在这种情况下,小的输入变化会导致显著的性能下降.
  • 现有的对抗性攻击方法往往不适合细分任务,无法利用空间细微差别或内部结构依赖.

研究的目的:

  • 开发一种专门为分段任何模型 (SAM) 量身定制的新型对抗性攻击战略.
  • 通过利用模型固有的结构特征来解决细分中的当前对抗技术的局限性.

主要方法:

  • 引入区域导向攻击 (RGA),这是针对SAM设计的一种新方法.
  • 利用区域导向地图 (RGM) 来指导细分区域内的目标扰动.
  • 实施RGA以分割大型细分并扩展较小的细分,诱导错误的细分输出.

主要成果:

  • 在白盒和黑盒对抗性攻击场景中,RGA表现出高的成功率.
  • 该攻击有效地通过利用特定区域的漏洞来操纵SAM的细分.
  • 实验验证证证实了RGA在损害SAM性能方面的有效性.

结论:

  • 拟议的区域引导攻击 (RGA) 对分段任何模型 (SAM) 构成重大威胁.
  • 发展强大的防御机制,以应对像RGA这样复杂的对抗性攻击,是非常必要的.
  • 这些发现强调了理解和减轻高级图像细分模型中的漏洞的重要性.