1. The limitations of deep learning in adversarial settings;papernot;2016 IEEE European Symposium on Security and Privacy (EuroS&P),2015
2. Towards robust detection of adversarial examples;pang;Advances in neural information processing systems,2018
3. On detecting adversarial perturbations;metzen;International Conference on Learning Representations (ICLR),2017
4. The curse of concentration in robust learning:Evasion and poisoning attacks from concentration of measure;mahloujifar;Proceedings of the AAAI Conference on Artificial Intelligence,2018
5. Towards deep learning models resistant to adversarial attacks;madry;2018 International Conference on Learning Representations,2018