Deep Defense: Training DNNs with Improved Adversarial Robustness
Published in Dec, 2018
Yan, Ziang*, Yiwen Guo*, and Changshui Zhang. "DeepDefense: Training Deep Neural Networks with Improved Robustness." NeurIPS 2018.
Deep Defense is recipe to improve the robustness of DNNs to adversarial perturbations. We integrate an adversarial perturbation-based regularizer into the training objective, such that the obtained models learn to resist potential attacks in a principled way.