# Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness Source: [Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness]() Collection index: [llms.txt]() Data updated: 2026-01-23T05:00:04.920Z Authors: Yufei Song, Ziqi Zhou, Menghao Deng, Yifan Hu, Shengshan Hu, Minghui Li, Leo Yu Zhang Published: 2026-01-21T12:52:09.000Z ## Abstract Existing segmentation models exhibit significant vulnerability to adversarial attacks.To improve robustness, adversarial training incorporates adversarial examples into model training. However, existing attack methods consider only global semantic information and ignore contextual semantic relationships within the samples, limiting the effectiveness of adversarial training. To address this issue, we propose EroSeg-AT, a vulnerability-aware adversarial training framework that leverages EroSeg to generate adversarial examples. EroSeg first selects sensitive pixels based on pixel-level confidence and then progressively propagates perturbations to higher-confidence pixels, effectively disrupting the semantic consistency of the samples. Experimental results show that, compared to existing methods, our approach significantly improves attack effectiveness and enhances model robustness under adversarial training. ## 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. - [Semantic Segmentation on Cityscapes](): Semantic segmentation; Cityscapes; mIoU: 53.35. ## Original sources and implementation [Original paper]() [PDF]()