Dan Kondratyuk

Replicate results seen in arXiv paper

9

There are some preliminary results of the one-pixel attack performed on Cifar10 in the repo, but it is not quite as comprehensive as seen in https://arxiv.org/abs/1710.08864. It would be nice...

The paper, [Attacking Convolutional Neural Network using Differential Evolution](https://arxiv.org/abs/1804.07062v1), explains how to tweak the one pixel attack to produce adversarial images that minimize the amount of perturbation in an image....

Download ImageNet images automatically

4

Modify [2_one-pixel-attack-imagenet.ipynb](https://github.com/Hyperparticle/one-pixel-attack-keras/blob/master/2_one-pixel-attack-imagenet.ipynb) to download a sample subset of ImageNet files with appropriate labels. The files should be preprocessed as to be ready for the attack.

Similar to [1_one-pixel-attack-cifar10.ipynb](https://github.com/Hyperparticle/one-pixel-attack-keras/blob/master/1_one-pixel-attack-cifar10.ipynb), perform a series of targeted/targeted adversarial attacks using differential evolution and collect results. This is a continuation of #3.

It would be useful to integrate the [UDify model](https://github.com/Hyperparticle/udify) directly into AllenNLP as a PR, as the code merely extends the library to handle a few extra features. Since the...