mlsanityData to 7 Oct 2026

Adversarial Examples for Semantic Image Segmentation

arXiv 1703.01101 ↗First posted 3 Mar 2017stat.ML cs.CR cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic segmentation. We show how existing adversarial attackers can be transferred to this task and that it is possible to create imperceptible adversarial perturbations that lead a deep network to misclassify almost all pixels of a chosen class while leaving network prediction nearly unchanged outside this class.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 14; 2022: 5; 2023: 6; 2024: 8.

33 papers.

Sort:

By area:

  1. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  2. 20213DB: A Framework for Debugging Computer Vision Modelscited by 31
  3. 2021TAFIM: Targeted Adversarial Attacks against Facial Image Manipulationscited by 25
  4. 2022Proximal Splitting Adversarial Attacks for Semantic Segmentationcited by 23
  5. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 22
  6. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  7. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  8. 2021Stabilized Medical Image Attackscited by 10
  9. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  10. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10
  11. 2021Improving Model Robustness with Latent Distribution Locally and Globallycited by 9
  12. 2024Practical Region-level Attack against Segment Anything Modelscited by 9
21 more
  1. 2021IPatch: A Remote Adversarial Patchcited by 7
  2. 2021Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extractioncited by 5
  3. 2022Smoothed Embeddings for Certified Few-Shot Learningcited by 5
  4. 2023Influencer Backdoor Attack on Semantic Segmentationcited by 5
  5. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5
  6. 2023A Review of Adversarial Attacks in Computer Visioncited by 5
  7. 2024Segment-Anything Models Achieve Zero-shot Robustness in Autonomous Drivingcited by 5
  8. 2024Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentationcited by 5
  9. 2021Consistent Semantic Attacks on Optical Flowcited by 4
  10. 2023Transferable Attack for Semantic Segmentationcited by 4
  11. 2022Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaversescited by 3
  12. 2021Adversarial Heart Attack: Neural Networks Fooled to Segment Heart Symbols in Chest X-Ray Imagescited by 1
  13. 2021Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackerscited by 1
  14. 2022A Human-in-the-Middle Attack against Object Detection Systemscited by 1
  15. 2023On Evaluating the Adversarial Robustness of Semantic Segmentation Modelscited by 1
  16. 2024MITS-GAN: Safeguarding Medical Imaging from Tampering with Generative Adversarial Networkscited by 1
  17. 2024Delving into Decision-based Black-box Attacks on Semantic Segmentationcited by 1
  18. 2024Evaluating the Adversarial Robustness of Semantic Segmentation: Trying Harder Pays Offcited by 1
  19. 2021Chameleon: A Semi-AutoML framework targeting quick and scalable development and deployment of production-ready ML systems for SMEscited by 0
  20. 2021M2GAN: A Multi-Stage Self-Attention Network for Image Rain Removal on Autonomous Vehiclescited by 0
  21. 2021Correlation between image quality metrics of magnetic resonance images and the neural network segmentation accuracycited by 0