Saved in:
Bibliographic Details
Main Authors: Salhab, Wissam, Ameyed, Darine, Mcheick, Hamid, Jaafar, Fehmi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.12713
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912647044136960
author Salhab, Wissam
Ameyed, Darine
Mcheick, Hamid
Jaafar, Fehmi
author_facet Salhab, Wissam
Ameyed, Darine
Mcheick, Hamid
Jaafar, Fehmi
contents Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robustness. The proposed approach leverages the principles of self-supervised learning, allowing the model to learn useful representations from unlabeled data. Combined with graph-theoretical techniques, this enables the more efficient identification and categorization of OOD samples. Compared to existing state-of-the-art methods, this approach achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) = 0.99.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Salhab, Wissam
Ameyed, Darine
Mcheick, Hamid
Jaafar, Fehmi
Artificial Intelligence
Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robustness. The proposed approach leverages the principles of self-supervised learning, allowing the model to learn useful representations from unlabeled data. Combined with graph-theoretical techniques, this enables the more efficient identification and categorization of OOD samples. Compared to existing state-of-the-art methods, this approach achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) = 0.99.
title Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
topic Artificial Intelligence
url https://arxiv.org/abs/2510.12713