mlsanityData to 14 Oct 2026

Proximal Splitting Adversarial Attacks for Semantic Segmentation

arXiv 2206.07179 ↗First posted 14 Jun 2022cs.LG cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Classification has been the focal point of research on adversarial attacks, but only a few works investigate methods suited to denser prediction tasks, such as semantic segmentation. The methods proposed in these works do not accurately solve the adversarial segmentation problem and, therefore, overestimate the size of the perturbations required to fool models. Here, we propose a white-box attack for these models based on a proximal splitting to produce adversarial perturbations with much smaller ℓ_∞ norms. Our attack can handle large numbers of constraints within a nonconvex minimization framework via an Augmented Lagrangian approach, coupled with adaptive constraint scaling and masking strategies. We demonstrate that our attack significantly outperforms previously proposed ones, as well as classification attacks that we adapted for segmentation, providing a first comprehensive benchmark for this dense task.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 26 of its 53 references that are in the map. First posted on arXiv 14 Jun 2022.

Builds on

26 of 53 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  9. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2016Adversarial Machine Learning at Scalecited by 936
  12. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
14 more
  1. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  2. 2021Are Transformers More Robust Than CNNs?cited by 187
  3. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  4. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  5. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  6. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  7. 2019Accurate, reliable and fast robustness evaluationcited by 43
  8. 2020Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentationcited by 38
  9. 2017Adversarial Examples for Semantic Image Segmentationcited by 33
  10. 2020Augmented Lagrangian Adversarial Attackscited by 28
  11. 2019Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentationcited by 26
  12. 2018Trust Region Based Adversarial Attack on Neural Networkscited by 11
  13. 2021PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attackcited by 8
  14. 2018Proximal Activation of Smooth Functions in Splitting Algorithms for Convex Image Recoverycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 6; 2025: 6; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
  2. 2023Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Modelscited by 12
  3. 2024Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusioncited by 11
  4. 2023Adversarial Attacks on Video Object Segmentation with Hard Region Discoverycited by 9
  5. 2023Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentationcited by 9
  6. 2024Practical Region-level Attack against Segment Anything Modelscited by 9
  7. 2023Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentationcited by 5
  8. 2023A Review of Adversarial Attacks in Computer Visioncited by 5
  9. 2023Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Modelscited by 5
  10. 2025Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivativescited by 2
  11. 2023On Evaluating the Adversarial Robustness of Semantic Segmentation Modelscited by 1
  12. 2024Delving into Decision-based Black-box Attacks on Semantic Segmentationcited by 1
11 more
  1. 2024Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Offcited by 1
  2. 2024Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysiscited by 1
  3. 2025Cross-Model Transferability of Adversarial Patches in Real-time Segmentation for Autonomous Drivingcited by 1
  4. 2025Adversarial Robustness of Discriminative Self-Supervised Learning in Visioncited by 1
  5. 2025Active Adversarial Noise Suppression for Image Forgery Localizationcited by 1
  6. 2025Fast and Flexible Robustness Certificates for Semantic Segmentationcited by 1
  7. 2023Trainwreck: A damaging adversarial attack on image classifierscited by 0
  8. 2024Multi-style conversion for semantic segmentation of lesions in fundus images by adversarial attackscited by 0
  9. 2025Proxy-Embedding as an Adversarial Teacher: An Embedding-Guided Bidirectional Attack for Referring Expression Segmentation Modelscited by 0
  10. 2026Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbationcited by 0
  11. 2026IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attackscited by 0