1. Understanding and improving fast adversarial training;Andriushchenko,2020
2. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples;Athalye
3. Synthesizing robust adversarial examples;Athalye
4. Universal Adversarial Training with Class-Wise Perturbations
5. APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection