Code for "Adversarial Robustness as a Prior on Learned Representations"

Running the notebooks

Steps to run the notebooks (for now, requires CUDA):

Clone this repository with --recurse-submodules to include submodules (--recursive pre-Git 2.13)
Download our models: here
Make a models folder in the main repository folder, and save the checkpoints there
Install all the required packages with pip install -r requirements.txt
Edit user_constants.py to point to PyTorch-formatted versions of the CIFAR and ImageNet datasets
Start a jupyter notebook server: jupyter notebook . --ip 0.0.0.0

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
README.md		README.md
direct_feature_visualization.ipynb		direct_feature_visualization.ipynb
feature_addition.ipynb		feature_addition.ipynb
image_inversion.ipynb		image_inversion.ipynb
interpolation.ipynb		interpolation.ipynb
maximizing_inputs.ipynb		maximizing_inputs.ipynb
requirements.txt		requirements.txt
user_constants.py		user_constants.py