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

相关实验视频

Updated: May 5, 2026

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury
10:33

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Published on: August 14, 2019

8.2K

对文本到图像扩散模型的对抗性歧视性攻击.

Hanxiao Wu1, Shengwu Xiong2, Dong Yi3

  • 1School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, 430070, Hubei, China; Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 101408, China; Wuhan AI Research, Wuhan, 430000, Hubei, China.

Neural networks : the official journal of the International Neural Network Society
|February 18, 2026
PubMed
概括

相关概念视频

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

8.6K
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...
8.6K

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

Visible-Light-Driven Photoredox-Catalyzed [4 + 2] Annulation of Unsaturated α-Bromocarbonyls with α-Substituted Styrenes.

The Journal of organic chemistry·2026
Same author

A Biological Alignment Framework for Interpreting Anti-Inflammatory Cardiovascular Trials in Atherosclerosis.

Aging and disease·2026
Same author

Discovery of Novel Plant O-Methyltransferases for Directed Methylation of Flavonoids and Stilbenoids.

Chembiochem : a European journal of chemical biology·2026
Same author

Ethical considerations and management strategies for fertility preservation in women of reproductive age with malignant tumors: Chinese practices and perspectives.

Frontiers in endocrinology·2026
Same author

Photoredox-Catalyzed Transamidation of Amides with Weakly Nucleophilic Aromatic Amines.

The Journal of organic chemistry·2026
Same author

AnyDesign: Versatile area fashion editing via mask-free diffusion.

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
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
查看所有相关文章
此摘要是机器生成的。

一种新的攻击方法,即对抗性歧视性攻击 (ADAtk),有效地绕过了概念删除扩散模型中的安全机制. ADAtk以超过90%的成功率生成被归类为"不安全用于工作" (NSFW) 的图像,揭示了当前AI安全技术的漏洞.

科学领域:

  • 人工智能的人工智能
  • 计算机视觉 计算机视觉
  • 生成型模型 生成型模型

背景情况:

  • 概念删除的传播模型在防止不安全工作 (NSFW) 内容生成方面面临挑战.
  • 现有的攻击方法专注于图像相似性,这不能保证成功的NSFW重建.

研究的目的:

  • 提出一种新的攻击方法,即对抗性歧视性攻击 (ADAtk),以揭露概念删除扩散模型中的漏洞.
  • 通过采用歧视性方法来解决现有的以代为中心的攻击的局限性.

主要方法:

  • ADAtk通过在模型的潜在空间中创建对抗性干扰来优化生成NSFW内容的可能性.
  • 该方法引导图像重建到目标歧视类,旨在将其归类为不适当的.

主要成果:

  • 在绕过当前的内部安全机制方面,ADAtk取得了超过90%的成功率.
  • 这次攻击成功地揭示了扩散模型现有的概念除技术的关键局限性.

结论:

  • ADAtk为提高文本到图像生成系统的安全性和可靠性提供了关键的见解.
  • 这些发现为开发更安全的生成人工智能模型和强大的安全协议铺平了道路.
关键词:
人工智能安全AI安全敌对的歧视性攻击攻击.概念消除的扩散模型文本到图像的生成.

相关实验视频

Last Updated: May 5, 2026

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury
10:33

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Published on: August 14, 2019

8.2K