Adversarial Examples as an Input-Fault Tolerance Problem

Fully self-contained source code release including pre-trained checkpoints and a test set for reproducing all figures and experiments in the paper.

The initial release is in PyTorch, with a TensorFlow notebook coming soon.

The main dependencies are

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
ckpt		ckpt
dataset		dataset
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
adef_on_svhn_funcs.py		adef_on_svhn_funcs.py
advex_input_fault_tolerance_nips18_secml.pdf		advex_input_fault_tolerance_nips18_secml.pdf
cnn_model_pytorch.py		cnn_model_pytorch.py
deformation.py		deformation.py
ft_plot.py		ft_plot.py
ft_utils.py		ft_utils.py
svhn_advex_fault_tolerance_pytorch.ipynb		svhn_advex_fault_tolerance_pytorch.ipynb
svhn_generate_plots_for_paper.ipynb		svhn_generate_plots_for_paper.ipynb

Provide feedback