Building Trust in Artificial Intelligence: A Necessity for Railway Applications
cs.AI
Submitted: 2026-09-16
Updated: 2026-09-16
Comments: Transport Research Arena 2026, pre-print
Project page: https://christophm.github.io/interpretable-ml-book
License: http://creativecommons.org/licenses/by/4.0/
The gist: Artificial Intelligence (AI) is currently only applied to non-safety critical applications due to the strict standards and regulations for railway industries.
Terminology
Abstract
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.
Sources
- Scalable, Technology-Agnostic Diagnosis and Predictive Maintenance for Point Machine using Deep Learning
- Track Component Failure Detection Using Data Analytics over existing STDS Track Circuit data
- CVCM Track Circuits Pre-emptive Failure Diagnostics for Predictive Maintenance Using Deep Neural Networks
- Intriguing properties of neural networks
- Explaining and Harnessing Adversarial Examples
- It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Certified Adversarial Robustness via Randomized Smoothing
- Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
- Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification
- Sorting out Lipschitz function approximation
- Spectral Normalization for Generative Adversarial Networks
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
- Robustness May Be at Odds with Accuracy
- Consistent Individualized Feature Attribution for Tree Ensembles
- What You See is What You Classify: Black Box Attributions
- Xplique: A Deep Learning Explainability Toolbox
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection