# Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR Images

arXiv: https://arxiv.org/abs/2505.01884 · HTML: https://mlsanity.com/paper/2505.01884/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 76 references that are in the map.
- First posted on arXiv 3 May 2025.

## Builds on (most cited first, 23 of 23)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation](https://mlsanity.com/paper/1611.09326/) (2016)
- [Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation](https://mlsanity.com/paper/2307.08388/) (2023)
- [ML Attack Models: Adversarial Attacks and Data Poisoning Attacks](https://mlsanity.com/paper/2112.02797/) (2021)
- [Adversarial Examples on Segmentation Models Can be Easy to Transfer](https://mlsanity.com/paper/2111.11368/) (2021)
- [Imperfect Segmentation Labels: How Much Do They Matter?](https://mlsanity.com/paper/1806.04618/) (2018)
- [Estimating label quality and errors in semantic segmentation data via any model](https://mlsanity.com/paper/2307.05080/) (2023)
- [ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images](https://mlsanity.com/paper/2111.11567/) (2021)
- [A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking](https://mlsanity.com/paper/2306.12111/) (2023)
- [Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation](https://mlsanity.com/paper/2402.16164/) (2024)
- [VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise](https://mlsanity.com/paper/2406.03117/) (2024)
- [Enhancing coastal water body segmentation with Landsat Irish Coastal Segmentation (LICS) dataset](https://mlsanity.com/paper/2409.15311/) (2024)

## Built on by (most cited first, 2 of 2)

- [Lake Detection and Water Quality Estimation in Sentinel-2 Data](https://mlsanity.com/paper/2605.24515/) (2026)
- [Explainable Flood Segmentation on Sentinel-1 SAR1 Imagery Using CNN and Transformer Architectures](https://mlsanity.com/paper/2606.16302/) (2026)

## Abstract (arXiv)

Inland water body segmentation from Synthetic Aperture Radar (SAR) images is an important task needed for several applications, such as flood mapping. While SAR sensors capture data in all-weather conditions as high-resolution images, differentiating water and water-like surfaces from SAR images is not straightforward. Inland water bodies, such as large river basins, have complex geometry, which adds to the challenge of segmentation. U-Net is a widely used deep learning model for land-water segmentation of SAR images. In practice, manual annotation is often used to generate the corresponding water masks as ground truth. Manual annotation of the images is prone to label noise owing to data poisoning attacks, especially due to complex geometry. In this work, we simulate manual errors in the form of adversarial attacks on the U-Net model and study the robustness of the model to human errors in annotation. Our results indicate that U-Net can tolerate a certain level of corruption before its performance drops significantly. This finding highlights the crucial role that the quality of manual annotations plays in determining the effectiveness of the segmentation model. The code and the new dataset, along with adversarial examples for robust training, are publicly available. (GitHub link - https://github.com/GVCL/IWSeg-SAR-Poison.git)