mlsanityData to 14 Oct 2026

On Physical Adversarial Patches for Object Detection

arXiv 1906.11897 ↗First posted 20 Jun 2019cs.CV cs.CR cs.LGcited by 93

Not on the map. Why?

Abstract (arXiv)

In this paper, we demonstrate a physical adversarial patch attack against object detectors, notably the YOLOv3 detector. Unlike previous work on physical object detection attacks, which required the patch to overlap with the objects being misclassified or avoiding detection, we show that a properly designed patch can suppress virtually all the detected objects in the image. That is, we can place the patch anywhere in the image, causing all existing objects in the image to be missed entirely by the detector, even those far away from the patch itself. This in turn opens up new lines of physical attacks against object detection systems, which require no modification of the objects in a scene. A demo of the system can be found at https://youtu.be/WXnQjbZ1e7Y.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 21; 2023: 21; 2024: 16; 2025: 11; 2026: 6.

93 papers.

Sort:

By area:

  1. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  2. 2021Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detectioncited by 67
  3. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  4. 2022DTA: Physical Camouflage Attacks using Differentiable Transformation Networkcited by 51
  5. 2021Certified Patch Robustness via Smoothed Vision Transformerscited by 45
  6. 2023Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modelingcited by 41
  7. 2023DAP: A Dynamic Adversarial Patch for Evading Person Detectorscited by 40
  8. 2024Test-Time Backdoor Attacks on Multimodal Large Language Modelscited by 40
  9. 2023Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Drivingcited by 37
  10. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  11. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
  12. 2021Does enhanced shape bias improve neural network robustness to common corruptions?cited by 32
38 more
  1. 2022On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Drivingcited by 30
  2. 2022PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patchcited by 30
  3. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 29
  4. 2024Effectiveness Assessment of Recent Large Vision-Language Modelscited by 29
  5. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 25
  6. 2021Efficient Certified Defenses Against Patch Attacks on Image Classifierscited by 24
  7. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  8. 2021Meta Adversarial Training against Universal Patchescited by 19
  9. 2021Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devicescited by 18
  10. 2022REAP: A Large-Scale Realistic Adversarial Patch Benchmarkcited by 18
  11. 2021Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patchescited by 17
  12. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  13. 2022Certified Defences Against Adversarial Patch Attacks on Semantic Segmentationcited by 16
  14. 2021ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layerscited by 15
  15. 2023Physical Adversarial Attacks for Surveillance: A Surveycited by 15
  16. 2022Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detectioncited by 13
  17. 2024Object Detectors in the Open Environment: Challenges, Solutions, and Outlookcited by 13
  18. 2023AdvART: Adversarial Art for Camouflaged Object Detection Attackscited by 12
  19. 2023Dynamic Adversarial Attacks on Autonomous Driving Systemscited by 11
  20. 2024Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detectioncited by 11
  21. 2022Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysiscited by 10
  22. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  23. 2022Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Framecited by 9
  24. 2022CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Modelscited by 8
  25. 2023Threatening Patch Attacks on Object Detection in Optical Remote Sensing Imagescited by 8
  26. 2021IPatch: A Remote Adversarial Patchcited by 7
  27. 2024Flexible Physical Camouflage Generation Based on a Differential Approachcited by 7
  28. 2021Towards Adversarial Patch Analysis and Certified Defense against Crowd Countingcited by 6
  29. 2022Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detectioncited by 6
  30. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
  31. 2021Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNscited by 5
  32. 2022Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generatorcited by 5
  33. 2023Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectorscited by 5
  34. 2023DOEPatch: Dynamically Optimized Ensemble Model for Adversarial Patches Generationcited by 5
  35. 2024Multimodal Attack Detection for Action Recognition Modelscited by 5
  36. 2024I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectorscited by 5
  37. 2025Don't Lag, RAG: Training-Free Adversarial Detection Using RAGcited by 5
  38. 2021Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilitiescited by 4

50 most cited of 93 All 93 (JSON)