1. Explaining and harnessing adversarial examples;Goodfellow;ICLR,2015
2. Pixeldefend: Leveraging generative models to understand and defend against adversarial examples;Song;ICLR,2018
3. Defense-gan: Protecting classifiers against adversarial attacks using generative models;Samangouei;ICLR,2018
4. Online adversarial purification based on self-supervised learning;Shi;ICLR,2020