Adversarial-Deep-Learning / Adversarial-Deep-Learning/code-soup

Non targeted One Pixel Attack on random 500 samples

未关闭
#78 2 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
good first issue Priority:Medium Tutorials
主要语言
Jupyter Notebook
星标
17
派生
17
PR 合并指标
30 天内没有已合并 PR

描述

This will be one of the tutorials for One Pixel Attack using VGG16 and CIFAR10 (open to discussion if difficult). Try to include the visualizations in original paper. [Link](https://arxiv.org/pdf/1710.08864.pdf)

The following is the minimum requirement:-

- [ ] attack on 500 random samples
- [ ] Attack using 1/3/5 Pixel(s)
- [ ] Accuracy and Confidence analysis
- [ ] Pre and Post attack Image visualizations

贡献指南

打开贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。