Non targeted One Pixel Attack on random 500 samples

Adversarial-Deep-Learning / code-soup

This is a collection of algorithms and approaches used in the book adversarial deep learning

MIT License

18 stars 18 forks source link

Non targeted One Pixel Attack on random 500 samples #78

Open mehulrastogi opened 3 years ago

mehulrastogi commented 3 years ago

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

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

mehulrastogi commented 3 years ago

Refer to #79 for the fine tuned VGG16

Shreyas-Bhat commented 3 years ago

Hey, I would like to work on this