• Adversarial Examples Are Not Bugs, They Are Features
• Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
• Adversarial Self-Defense for Cycle-Consistent GANs
• A New Defense Against Adversarial Images: Turning a Weakness into a Strength
• Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
• Adversarial training for free!
• Certified Adversarial Robustness with Additive Noise
• Robustness to Adversarial Perturbations in Learning from Incomplete Data
• Unlabeled Data Improves Adversarial Robustness
• Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness
• Metric Learning for Adversarial Robustness
• Adversarial Robustness through Local Linearization