Saved in:
Bibliographic Details
Main Authors: Karunanayake, Naveen, Gunawardena, Ravin, Seneviratne, Suranga, Chawla, Sanjay
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.05219
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909163175542784
author Karunanayake, Naveen
Gunawardena, Ravin
Seneviratne, Suranga
Chawla, Sanjay
author_facet Karunanayake, Naveen
Gunawardena, Ravin
Seneviratne, Suranga
Chawla, Sanjay
contents 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. Robust OOD detection aims to differentiate between in-distribution (ID) data and OOD data, even when they are adversarially manipulated to deceive the OOD detector. Unified robustness seeks a single approach to make DNNs robust against both adversarial attacks and OOD inputs. Accordingly, first, we establish a taxonomy based on the concept of distributional shifts. This framework clarifies how robust OOD detection and unified robustness relate to other research areas addressing distributional shifts, such as OOD detection, open set recognition, and anomaly detection. Subsequently, we review existing work on robust OOD detection and unified robustness. Finally, we highlight the limitations of the existing work and propose promising research directions that explore adversarial and OOD inputs within a unified framework.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05219
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey
Karunanayake, Naveen
Gunawardena, Ravin
Seneviratne, Suranga
Chawla, Sanjay
Machine Learning
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. Robust OOD detection aims to differentiate between in-distribution (ID) data and OOD data, even when they are adversarially manipulated to deceive the OOD detector. Unified robustness seeks a single approach to make DNNs robust against both adversarial attacks and OOD inputs. Accordingly, first, we establish a taxonomy based on the concept of distributional shifts. This framework clarifies how robust OOD detection and unified robustness relate to other research areas addressing distributional shifts, such as OOD detection, open set recognition, and anomaly detection. Subsequently, we review existing work on robust OOD detection and unified robustness. Finally, we highlight the limitations of the existing work and propose promising research directions that explore adversarial and OOD inputs within a unified framework.
title Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey
topic Machine Learning
url https://arxiv.org/abs/2404.05219