DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation

arXiv:2402.11120v1 Announce Type: new
Abstract: Distribution shifts and adversarial examples are two major challenges for deploying machine learning models. While these challenges have been studied individually, their combination is an important topic that remains relatively under-explored. In this work, we study the problem of adversarial robustness under a common setting of distribution shift - unsupervised domain adaptation (UDA). Specifically, given a labeled source domain $D_S$ and an unlabeled target domain $D_T$ with related but different distributions, the goal is to …

abstract adversarial adversarial examples arxiv challenges combination cs.cv cs.lg dart distribution domain domain adaptation examples machine machine learning machine learning models major robust robustness stat.ml study type unsupervised work