# Probabilistic Robustness Analysis in High Dimensional Space: Application to Semantic Segmentation Network Source: [Probabilistic Robustness Analysis in High Dimensional Space: Application to Semantic Segmentation Network]() Collection index: [llms.txt]() Data updated: 2025-11-19T05:02:23.880Z Authors: Navid Hashemi, Samuel Sasaki, Diego Manzanas Lopez, Lars Lindemann, Ipek Oguz, Meiyi Ma, Taylor T. Johnson Published: 2025-09-15T12:25:25.000Z ## Abstract Semantic segmentation networks (SSNs) are central to safety-critical applications such as medical imaging and autonomous driving, where robustness under uncertainty is essential. However, existing probabilistic verification methods often fail to scale with the complexity and dimensionality of modern segmentation tasks, producing guarantees that are overly conservative and of limited practical value. We propose a probabilistic verification framework that is architecture-agnostic and scalable to high-dimensional input-output spaces. Our approach employs conformal inference (CI), enhanced by a novel technique that we call the \\textbf{clipping block}, to provide provable guarantees while mitigating the excessive conservatism of prior methods. Experiments on large-scale segmentation models across CamVid, OCTA-500, Lung Segmentation, and Cityscapes demonstrate that our framework delivers reliable safety guarantees while substantially reducing conservatism compared to state-of-the-art approaches on segmentation tasks. We also provide a public GitHub repository (https://github.com/Navidhashemicodes/SSN\_Reach\_CLP\_Surrogate) for this approach, to support reproducibility. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()