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

迈向无处不在的可靠分类 - 对抗鲁棒性和分布外检测的联合框架

• 批准号: 464101476
• 负责人: Professor Dr. Matthias Hein
• 金额: --
• 依托单位: Professur für Maschinelles Lernen
• 依托单位国家: 德国
• 项目类别: Priority Programmes
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/464101476?language=en
• 关键词: Towards; everywhere; reliable; classification; joint

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.

到目前为止，对抗鲁棒性和分布外（OOD）检测已经被分开处理。然而，在我们看来，将这些问题分开是人为的，因为它们是内在地相互联系的。只有超越Madry等人提出的经典对抗训练框架，并将OOD检测和对抗鲁棒性合并到一个框架中，才有可能在训练时使用的威胁模型之外推广对抗鲁棒性的进步。