mlsanityData to 14 Oct 2026

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation

arXiv 2603.20777 ↗First posted 21 Mar 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 26 references that are in the map. First posted on arXiv 21 Mar 2026.

Builds on

23 of 26 references.

References · 23

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  9. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  10. 2020BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentationcited by 294
  11. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  12. 2018Boundary loss for highly unbalanced segmentationcited by 190
11 more
  1. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  2. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  3. 2022PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllerscited by 84
  4. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  5. 2021On Improving Adversarial Transferability of Vision Transformerscited by 70
  6. 2022When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecturecited by 64
  7. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  8. 2022Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?cited by 49
  9. 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
  10. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10
  11. 2025Cross-Model Transferability of Adversarial Patches in Real-time Segmentation for Autonomous Drivingcited by 1

Built on by

Not cited yet.