Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dario, Mathieu, Chenevier, Florent, Delmas, Kévin, Guerin, Joris, Guiochet, Jérémie
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.26411
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913072549986304
author Dario, Mathieu
Chenevier, Florent
Delmas, Kévin
Guerin, Joris
Guiochet, Jérémie
author_facet Dario, Mathieu
Chenevier, Florent
Delmas, Kévin
Guerin, Joris
Guiochet, Jérémie
contents Runtime monitoring is essential to ensure the safety of ML applications in safety-critical domains. However, current research is fragmented, with independent methods emerging from different communities. In this paper, we propose a unified framework categorising runtime monitoring approaches into three distinct types: Operational Design Domain (ODD) monitoring, which ensures compliance with expected operating conditions; Out-of-Distribution (OOD) monitoring, which rejects inputs that deviate from the training data; and Out-of-Model-Scope (OMS) monitoring, which detects anomalous model behaviour based its internal states or outputs. We demonstrate the benefits of this categorization with a dedicated experiment on an aeronautical safety-critical application: runway detection during landing. This framework facilitates design of monitoring activities, with complementary categories of monitors, and enables evaluation and comparison of different monitors using common, safety-oriented metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26411
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing
Dario, Mathieu
Chenevier, Florent
Delmas, Kévin
Guerin, Joris
Guiochet, Jérémie
Machine Learning
Runtime monitoring is essential to ensure the safety of ML applications in safety-critical domains. However, current research is fragmented, with independent methods emerging from different communities. In this paper, we propose a unified framework categorising runtime monitoring approaches into three distinct types: Operational Design Domain (ODD) monitoring, which ensures compliance with expected operating conditions; Out-of-Distribution (OOD) monitoring, which rejects inputs that deviate from the training data; and Out-of-Model-Scope (OMS) monitoring, which detects anomalous model behaviour based its internal states or outputs. We demonstrate the benefits of this categorization with a dedicated experiment on an aeronautical safety-critical application: runway detection during landing. This framework facilitates design of monitoring activities, with complementary categories of monitors, and enables evaluation and comparison of different monitors using common, safety-oriented metrics.
title Unifying Runtime Monitoring Approaches for Safety-Critical Machine Learning: Application to Vision-Based Landing
topic Machine Learning
url https://arxiv.org/abs/2604.26411