# A Certified Radius-Guided Attack Framework to Image Segmentation Models

arXiv: https://arxiv.org/abs/2304.02693 · HTML: https://mlsanity.com/paper/2304.02693/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 98 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 30 of 67)

- [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)
- [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)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Efficient Neural Network Robustness Certification with General Activation Functions](https://mlsanity.com/paper/1811.00866/) (2018)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers](https://mlsanity.com/paper/1906.04584/) (2019)
- [Certified Defenses against Adversarial Examples](https://mlsanity.com/paper/1801.09344/) (2018)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [Towards Fast Computation of Certified Robustness for ReLU Networks](https://mlsanity.com/paper/1804.09699/) (2018)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks](https://mlsanity.com/paper/1705.01320/) (2017)
- [High-Resolution Representations for Labeling Pixels and Regions](https://mlsanity.com/paper/1904.04514/) (2019)
- [Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach](https://mlsanity.com/paper/1801.10578/) (2018)
- [Certified Adversarial Robustness with Additive Noise](https://mlsanity.com/paper/1809.03113/) (2018)
- [Semidefinite relaxations for certifying robustness to adversarial examples](https://mlsanity.com/paper/1811.01057/) (2018)

## Built on by (most cited first, 5 of 5)

- [Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation](https://mlsanity.com/paper/2310.17436/) (2023)
- [Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence](https://mlsanity.com/paper/2304.04343/) (2023)
- [Learning Robust and Privacy-Preserving Representations via Information Theory](https://mlsanity.com/paper/2412.11066/) (2024)
- [Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis](https://mlsanity.com/paper/2408.10021/) (2024)
- [IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attacks](https://mlsanity.com/paper/2607.27465/) (2026)

## Abstract (arXiv)

Image segmentation is an important problem in many safety-critical applications. Recent studies show that modern image segmentation models are vulnerable to adversarial perturbations, while existing attack methods mainly follow the idea of attacking image classification models. We argue that image segmentation and classification have inherent differences, and design an attack framework specially for image segmentation models. Our attack framework is inspired by certified radius, which was originally used by defenders to defend against adversarial perturbations to classification models. We are the first, from the attacker perspective, to leverage the properties of certified radius and propose a certified radius guided attack framework against image segmentation models. Specifically, we first adapt randomized smoothing, the state-of-the-art certification method for classification models, to derive the pixel's certified radius. We then focus more on disrupting pixels with relatively smaller certified radii and design a pixel-wise certified radius guided loss, when plugged into any existing white-box attack, yields our certified radius-guided white-box attack. Next, we propose the first black-box attack to image segmentation models via bandit. We design a novel gradient estimator, based on bandit feedback, which is query-efficient and provably unbiased and stable. We use this gradient estimator to design a projected bandit gradient descent (PBGD) attack, as well as a certified radius-guided PBGD (CR-PBGD) attack. We prove our PBGD and CR-PBGD attacks can achieve asymptotically optimal attack performance with an optimal rate. We evaluate our certified-radius guided white-box and black-box attacks on multiple modern image segmentation models and datasets. Our results validate the effectiveness of our certified radius-guided attack framework.