Towards everywhere reliable classification - A joint framework for adversarial robustness and out-of-distribution detection

点击翻译按钮获取中文摘要

Adversarial robustness and out-of-distribution (OOD) detection have been treated separately so far. However, the separation of these problems is in our point of view artificial as they are inherently linked to each other. Advances in in adversarial robustness generalizing beyond the threat models used at training time seem possible only by going beyond the classical adversarial training framework proposed by Madry et al. and merging OOD detection and adversarial robustness in a single framework.