# Susceptibility of Adversarial Attack on Medical Image Segmentation Models

arXiv: https://arxiv.org/abs/2401.11224 · HTML: https://mlsanity.com/paper/2401.11224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 20 Jan 2024.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [A survey of loss functions for semantic segmentation](https://mlsanity.com/paper/2006.14822/) (2020)
- [Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems](https://mlsanity.com/paper/1907.10456/) (2019)
- [On the Robustness of Semantic Segmentation Models to Adversarial Attacks](https://mlsanity.com/paper/1711.09856/) (2017)
- [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017)
- [Backdoor Attacks on Vision Transformers](https://mlsanity.com/paper/2206.08477/) (2022)

## Abstract (arXiv)

The nature of deep neural networks has given rise to a variety of attacks, but little work has been done to address the effect of adversarial attacks on segmentation models trained on MRI datasets. In light of the grave consequences that such attacks could cause, we explore four models from the U-Net family and examine their responses to the Fast Gradient Sign Method (FGSM) attack. We conduct FGSM attacks on each of them and experiment with various schemes to conduct the attacks. In this paper, we find that medical imaging segmentation models are indeed vulnerable to adversarial attacks and that there is a negligible correlation between parameter size and adversarial attack success. Furthermore, we show that using a different loss function than the one used for training yields higher adversarial attack success, contrary to what the FGSM authors suggested. In future efforts, we will conduct the experiments detailed in this paper with more segmentation models and different attacks. We will also attempt to find ways to counteract the attacks by using model ensembles or special data augmentations. Our code is available at https://github.com/ZhongxuanWang/adv_attk