RobustRailNet: Architecture-Driven Adversarial Robustness for Safety-Critical Railway Obstacle Perception
Open Access
- 3 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 56138-56154
Abstract
State-of-the-art architectures for automated railway safety surveillance achieve high benchmark accuracies; however, such systems are systematically vulnerable to adversarial perturbations. Current approaches focus on adversarial training, while other aspects, such as architecture design, are overlooked as robustness mechanisms. We propose RobustRailNet, a novel architecture for the robust and high-performance classification of railway obstacles. The proposed approach builds upon domain-relevant characteristics such as high-frequency textures, spatially coherent structures, and global context. RobustRailNet is evaluated against seven white-box adversarial attacks, including gradient-based, optimization-based, and patch-based methods, representing a worst-case assumption for model vulnerability. The evaluation is conducted on a diverse dataset comprising multiple railway obstacle types. RobustRailNet achieves a highly significant mean robustness gain of up to 66.89 percentage points compared to the state-of-the-art while maintaining a mean balanced accuracy of 99.52%. The results demonstrate that adversarial vulnerability arises from architectural design and is not exclusively linked to training data or strategies. Architectural optimization should therefore be seen as a necessity rather than a possibility for the design of robust, safety-critical systems. When developing and deploying such architectures in practice, the influence of the architecture should be taken into account upfront, rather than attempting to achieve robustness exclusively through ex post retraining.Keywords
Funding Information
- Open-Access-Publication-Fund of the Helmut-Schmidt-University/University of the Federal Armed Forces Hamburg
This publication has 47 references indexed in Scilit:
- Adversarial machine learning: a review of methods, tools, and critical industry sectorsArtificial Intelligence Review, 2025
- An unmanned aerial vehicle captured dataset for railroad segmentation and obstacle detectionScientific Data, 2024
- UAV-based studies in railway infrastructure monitoringAutomation in Construction, 2024
- On the right track? Energy use, carbon emissions, and intensities of world rail transportation, 1840–2020Applied Energy, 2024
- Real-time railroad track components inspection framework based on YOLO-NAS and edge computingIOP Conference Series: Earth and Environmental Science, 2024
- RailSegVITNet: A lightweight VIT-based real-time track surface segmentation network for improving railroad safetyJournal of King Saud University Computer and Information Sciences, 2024
- Safety analysis in a modern railway settingSafety Science, 2018
- The economics of railway safetyResearch in Transportation Economics, 2013
- Fast Noise Variance EstimationComputer Vision and Image Understanding, 1996
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992