mlsanityData to 14 Oct 2026

Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey

arXiv 2206.08304 ↗First posted 16 Jun 2022cs.CV cs.CR cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks in deep learning models, especially for safety-critical systems, are gaining more and more attention in recent years, due to the lack of trust in the security and robustness of AI models. Yet the more primitive adversarial attacks might be physically infeasible or require some resources that are hard to access like the training data, which motivated the emergence of patch attacks. In this survey, we provide a comprehensive overview to cover existing techniques of adversarial patch attacks, aiming to help interested researchers quickly catch up with the progress in this field. We also discuss existing techniques for developing detection and defences against adversarial patches, aiming to help the community better understand this field and its applications in the real world.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 126 of its 199 references that are in the map. First posted on arXiv 16 Jun 2022.

Builds on

126 of 199 references.

References · 126

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  8. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  10. 2013Intriguing properties of neural networkscited by 5,155
  11. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  12. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
38 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2015Fast R-CNNcited by 2,933
  6. 2018YOLOv3: An Incremental Improvementcited by 2,659
  7. 2016Pyramid Scene Parsing Networkcited by 2,479
  8. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  13. 2016Adversarial examples in the physical worldcited by 1,769
  14. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  15. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  16. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  17. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  18. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  19. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  20. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  21. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  22. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  23. 2017Deep Image Priorcited by 1,098
  24. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  25. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  26. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  27. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  28. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  29. 2016Universal adversarial perturbationscited by 784
  30. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  31. 2017Dynamic Routing Between Capsulescited by 689
  32. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  33. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  34. 2017One pixel attack for fooling deep neural networkscited by 582
  35. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  36. 2017Adversarial Patchcited by 517
  37. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  38. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468

50 most cited of 126 All 126 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 3; 2025: 3; 2026: 1.

17 papers.

Sort:

By area:

  1. 2022Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptationcited by 98
  2. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 25
  3. 2025Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Modelscited by 22
  4. 2023Adv3D: Generating 3D Adversarial Examples for 3D Object Detection in Driving Scenarios with NeRFcited by 10
  5. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  6. 2024ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changescited by 5
  7. 2024Towards Formal Verification of Deep Neural Networks for Object Detectioncited by 4
  8. 2023A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Modelscited by 2
  9. 2023Flying Adversarial Patches: Manipulating the Behavior of Deep Learning-based Autonomous Multirotorscited by 1
  10. 2023NSA: Naturalistic Support Artifact to Boost Network Confidencecited by 1
  11. 2023Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patchescited by 1
  12. 2023Generating Visually Realistic Adversarial Patchcited by 1
5 more
  1. 2023Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Predictioncited by 0
  2. 2024Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noisescited by 0
  3. 2025IPG: Incremental Patch Generation for Generalized Adversarial Patch Trainingcited by 0
  4. 2025DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Modelscited by 0
  5. 2026Diffusion-Driven Deceptive Patches: Adversarial Manipulation and Forensic Detection in Facial Identity Verificationcited by 0