josh200501 / adversarial-robustness-public Goto Github PK
View Code? Open in Web Editor NEWThis project forked from dtak/adversarial-robustness-public
Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients"
Home Page: https://arxiv.org/abs/1711.09404
License: MIT License