# On Evaluating the Adversarial Robustness of Semantic Segmentation Models

arXiv: https://arxiv.org/abs/2306.14217 · HTML: https://mlsanity.com/paper/2306.14217/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 25 Jun 2023.

## Builds on (most cited first, 30 of 35)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [On the Robustness of Semantic Segmentation Models to Adversarial Attacks](https://mlsanity.com/paper/1711.09856/) (2017)
- [RayS: A Ray Searching Method for Hard-label Adversarial Attack](https://mlsanity.com/paper/2006.12792/) (2020)
- [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017)
- [Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations](https://mlsanity.com/paper/1801.08092/) (2018)
- [SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness](https://mlsanity.com/paper/2207.12391/) (2022)
- [Evaluating the Adversarial Robustness of Adaptive Test-time Defenses](https://mlsanity.com/paper/2202.13711/) (2022)
- [Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation](https://mlsanity.com/paper/2003.06555/) (2020)
- [Adversarial Examples for Semantic Image Segmentation](https://mlsanity.com/paper/1703.01101/) (2017)
- [Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2004.11072/) (2020)

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

- [Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models](https://mlsanity.com/paper/2311.14450/) (2023)

## Abstract (arXiv)

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense against adversarial perturbation, but the methodology of evaluating the robustness of the models is still lacking, compared to image classification. Here, we demonstrate that, just like in image classification, it is important to evaluate the models over several different and hard attacks. We propose a set of gradient based iterative attacks and show that it is essential to perform a large number of iterations. We include attacks against the internal representations of the models as well. We apply two types of attacks: maximizing the error with a bounded perturbation, and minimizing the perturbation for a given level of error. Using this set of attacks, we show for the first time that a number of models in previous work that are claimed to be robust are in fact not robust at all. We then evaluate simple adversarial training algorithms that produce reasonably robust models even under our set of strong attacks. Our results indicate that a key design decision to achieve any robustness is to use only adversarial examples during training. However, this introduces a trade-off between robustness and accuracy.