1. What causes optical flow networks to be vulnerable to physical ad-versarial attacks;schrodi;ArXiv Preprint,2021
2. Defense-gan: Protecting classifiers against adversarial attacks using generative models;samangouei;ArXiv Preprint,2018
3. Generative Adversarial Perturbations
4. Lower bounds on the robustness to adversarial perturbations;peck;Advances in neural information processing systems,0
5. Mixup inference: Better exploiting mixup to defend adversarial attacks;pang;ArXiv Preprint,2019