# Adversarial Heart Attack: Neural Networks Fooled to Segment Heart Symbols in Chest X-Ray Images

arXiv: https://arxiv.org/abs/2104.00139 · HTML: https://mlsanity.com/paper/2104.00139/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 25 of 25)

- [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)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [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)
- [Adversarial Examples Are a Natural Consequence of Test Error in Noise](https://mlsanity.com/paper/1901.10513/) (2019)
- [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017)
- [Adversarial examples from computational constraints](https://mlsanity.com/paper/1805.10204/) (2018)
- [Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations](https://mlsanity.com/paper/1911.01218/) (2019)
- [Adversarial Attacks Against Medical Deep Learning Systems](https://mlsanity.com/paper/1804.05296/) (2018)
- [Robustness to Adversarial Perturbations in Learning from Incomplete Data](https://mlsanity.com/paper/1905.13021/) (2019)
- [Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors](https://mlsanity.com/paper/2006.06356/) (2020)
- [Adversarial Examples for Semantic Image Segmentation](https://mlsanity.com/paper/1703.01101/) (2017)
- [Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation](https://mlsanity.com/paper/1907.13124/) (2019)
- [Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks](https://mlsanity.com/paper/1807.02905/) (2018)
- [One Bit Matters: Understanding Adversarial Examples as the Abuse of Redundancy](https://mlsanity.com/paper/1810.09650/) (2018)

## Built on by (most cited first, 1 of 1)

- [Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges](https://mlsanity.com/paper/2303.14133/) (2023)

## Abstract (arXiv)

Adversarial attacks consist in maliciously changing the input data to mislead the predictions of automated decision systems and are potentially a serious threat for automated medical image analysis. Previous studies have shown that it is possible to adversarially manipulate automated segmentations produced by neural networks in a targeted manner in the white-box attack setting. In this article, we studied the effectiveness of adversarial attacks in targeted modification of segmentations of anatomical structures in chest X-rays. Firstly, we experimented with using anatomically implausible shapes as targets for adversarial manipulation. We showed that, by adding almost imperceptible noise to the image, we can reliably force state-of-the-art neural networks to segment the heart as a heart symbol instead of its real anatomical shape. Moreover, such heart-shaping attack did not appear to require higher adversarial noise level than an untargeted attack based the same attack method. Secondly, we attempted to explore the limits of adversarial manipulation of segmentations. For that, we assessed the effectiveness of shrinking and enlarging segmentation contours for the three anatomical structures. We observed that adversarially extending segmentations of structures into regions with intensity and texture uncharacteristic for them presented a challenge to our attacks, as well as, in some cases, changing segmentations in ways that conflict with class adjacency priors learned by the target network. Additionally, we evaluated performances of the untargeted attacks and targeted heart attacks in the black-box attack scenario, using a surrogate network trained on a different subset of images. In both cases, the attacks were substantially less effective. We believe these findings bring novel insights into the current capabilities and limits of adversarial attacks for semantic segmentation.