Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey

arXiv:2404.05219v1 Announce Type: new
Abstract: Deep neural networks (DNNs) deployed in real-world applications can encounter out-of-distribution (OOD) data and adversarial examples. These represent distinct forms of distributional shifts that can significantly impact DNNs' reliability and robustness. Traditionally, research has addressed OOD detection and adversarial robustness as separate challenges. This survey focuses on the intersection of these two areas, examining how the research community has investigated them together. Consequently, we identify two key research directions: robust OOD detection and unified robustness. …

abstract adversarial adversarial examples applications arxiv challenges cs.lg data detection distribution examples forms impact networks neural networks reliability research robustness survey type world