mlsanityData to 14 Oct 2026

Transferable Attack for Semantic Segmentation

arXiv 2307.16572 ↗First posted 31 Jul 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and FGSM, do not transfer well to target models, making it necessary to study the transferable attacks, especially transferable attacks for semantic segmentation. We find two main factors to achieve transferable attack. Firstly, the attack should come with effective data augmentation and translation-invariant features to deal with unseen models. Secondly, stabilized optimization strategies are needed to find the optimal attack direction. Based on the above observations, we propose an ensemble attack for semantic segmentation to achieve more effective attacks with higher transferability. The source code and experimental results are publicly available via our project page: https://github.com/anucvers/TASS.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 74 of its 92 references that are in the map. First posted on arXiv 31 Jul 2023.

Builds on

74 of 92 references.

References · 74

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2023Segment Anythingcited by 8,234
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  11. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  4. 2016Pyramid Scene Parsing Networkcited by 2,479
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  8. 2021Vision Transformers for Dense Predictioncited by 1,803
  9. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  10. 2017Deformable Convolutional Networkscited by 1,488
  11. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  13. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  14. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  15. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  16. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  17. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  18. 2016Universal adversarial perturbationscited by 784
  19. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  20. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  21. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  22. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  23. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  24. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  25. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 442
  26. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
  27. 2019Panoptic-DeepLabcited by 363
  28. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  29. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  30. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  31. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  32. 2017Understanding Convolution for Semantic Segmentationcited by 168
  33. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 166
  34. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  35. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  36. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  37. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  38. 2020SegFix: Model-Agnostic Boundary Refinement for Segmentationcited by 97

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 1; 2026: 1.

4 papers.

  1. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10
  2. 2024Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncationcited by 2
  3. 2025FSPGD: Rethinking Black-box Attacks on Semantic Segmentationcited by 0
  4. 2026Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attackscited by 0