1. Intriguing Properties of Neural Networks;Szegedy,2013
2. Explaining and Harnessing Adversarial Examples;Goodfellow,2014
3. Towards Deep Learning Models Resistant to Adversarial Attacks;Madry,2017
4. Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks;Croce,2020
5. Towards evaluating the robustness of neural networks;Carlini,2017