摘要：
Samangouei P, Kabkab M, Chellappa R, et al. Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models.[J]. arXiv: Comput 阅读全文
摘要：
Athalye A, Carlini N, Wagner D, et al. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples[J]. arXiv: 阅读全文