12-21 (ICLR 2018) Defense-GAN:Protecting classifiers against adversarial attacks using generative models
12-21 (ICLR 2018) PixelDefend:Leveraging Generative Models to Understand and Defend against Adversarial Examples
12-21 (2017) Obfuscated Gradients Give a False Sense of Security:Circumventing Defenses to Adversarial Examples