SPATIALLY TRANSFORMED ADVERSARIAL EXAMPLES
SPATIALLY TRANSFORMED ADVERSARIAL EXAMPLES 本文发表在ICLR2018上 引言 传统的对抗样本生成方式都是加扰动，是一种像素值变换，本文提出一种空域变换生成对抗样本的方法stAdv，虽然基于此方法在传统的对抗样本生成评价指标中和原图像会有较大的 Lp L p 距离，但是从人的视觉感官上这种变换方式更真实，且更不容易被现有对抗攻击防御方法检测出来。 传统像素
相关文章
- 1. [paper]SPATIALLY TRANSFORMED ADVERSARIAL EXAMPLES
- 2. Paper Review: Adversarial Examples
- 3. [advGAN]Generating Adversarial Examples With Adversarial Networks
- 4. Generating Adversarial Examples with Adversarial Networks
- 5. Explaining and Harnessing Adversarial Examples
- 6. CS231n Lecture 16 | Adversarial Examples and Adversarial Training
- 7. Generating Adversarial Examples with Adversarial Networks阅读笔记
- 8. Adversarial Examples 对抗样本
- 9. [paper]ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD
- 10. explaining and harnessing adversarial examples(FGSM)
- 更多相关文章...
- • XPath Examples - XPath 教程
- • Rust 注释 - RUST 教程
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. [paper]SPATIALLY TRANSFORMED ADVERSARIAL EXAMPLES
- 2. Paper Review: Adversarial Examples
- 3. [advGAN]Generating Adversarial Examples With Adversarial Networks
- 4. Generating Adversarial Examples with Adversarial Networks
- 5. Explaining and Harnessing Adversarial Examples
- 6. CS231n Lecture 16 | Adversarial Examples and Adversarial Training
- 7. Generating Adversarial Examples with Adversarial Networks阅读笔记
- 8. Adversarial Examples 对抗样本
- 9. [paper]ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD
- 10. explaining and harnessing adversarial examples(FGSM)