Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders
arXiv: Learning, 2019.
Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial training is very expensive, and every time a model needs to be protected, such expensive training scheme needs to be performed. In this paper, we propose to app...More
PPT (Upload PPT)