Zeng, Huimin, Chen Zhu, Tom Goldstein, and Furong Huang. 2021. “Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-Uniform Attacks”. Proceedings of the AAAI Conference on Artificial Intelligence 35 (12):10815-23. https://doi.org/10.1609/aaai.v35i12.17292.