Adversarial-Deep-Learning / Adversarial-Deep-Learning/code-soup
Non targeted One Pixel Attack on random 500 samples
Ouverte
good first issue
Priority:Medium
Tutorials
- Langage dominant
- Jupyter Notebook
- Étoiles
- 17
- Forks
- 17
- Métriques de merge des PR
- Aucune PR mergée en 30 j
Description
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
Guide de contribution
Ouvrir le guide de contribution
Évaluation
Cette issue n'a pas encore été évaluée.