Building Trust in Artificial Intelligence: A Necessity for Railway Applications
Not on the map. Why?
Abstract (arXiv)
Artificial Intelligence (AI) is currently only applied to non-safety critical applications due to the strict standards and regulations for railway industries. We propose to review the three main fields necessary to increase trust in data science and AI algorithms and reach compliance: robustness, Operational Design Domain (ODD), and explainability. Robustness is the ability of an AI system to maintain its level of performance under any circumstances (ISO24029). ODDs allow the explicit definition of operating conditions under which a system is intended to operate, according to the recently published DIN DKE SPEC 99004. Explainability is the property of an AI system to express important factors influencing the AI system results in a way that humans can understand. Those 3 domains of research are already well investigated by nonrailway actors, with algorithms and methods ready to use for railway applications. A system view is necessary to ensure all trustworthy requirements interact continuously in a safe MLOps environment thereby fostering acceptance from regulators, operators and the public. Beyond safeguarding safety-critical applications, we aim to show that fostering deep trust in AI, as now required by regulatory frameworks worldwide, will unlock its full potential and transform the pace of adoption across mission-critical domains.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 47 references that are in the map. First posted on arXiv 16 Sep 2026.
Builds on
25 of 47 references.
References · 25
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
- 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
- 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
- 2018Sorting out Lipschitz function approximationcited by 213
13 more
- 2021Trustworthy AI: From Principles to Practicescited by 207
- 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 185
- 2016Robust Large Margin Deep Neural Networkscited by 118
- 2021A Comprehensive Evaluation Framework for Deep Model Robustnesscited by 42
- 2020Achieving robustness in classification using optimal transport with hinge regularizationcited by 27
- 2022Xplique: A Deep Learning Explainability Toolboxcited by 24
- 2022Adversarially-Aware Robust Object Detectorcited by 20
- 2022What You See is What You Classify: Black Box Attributionscited by 12
- 2023It Is All About Data: A Survey on the Effects of Data on Adversarial Robustnesscited by 9
- 2025Scalable, Technology-Agnostic Diagnosis and Predictive Maintenance for Point Machine using Deep Learningcited by 2
- 2023Towards a safe MLOps Process for the Continuous Development and Safety Assurance of ML-based Systems in the Railway Domaincited by 1
- 2025CVCM Track Circuits Pre-emptive Failure Diagnostics for Predictive Maintenance Using Deep Neural Networkscited by 1
- 2025Track Component Failure Detection Using Data Analytics over existing STDS Track Circuit datacited by 1
Built on by
Not cited yet.