mlsanityData to 7 Oct 2026

Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors

arXiv 2104.11101 ↗First posted 22 Apr 2021cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes. We sample triangular faces on a reference human mesh, and create an adversarial texture atlas over those faces. The adversarial texture is transferred to human meshes in various poses, which are rendered onto a collection of real-world background images. Contrary to the traditional patch-based adversarial attacks, where prior work attempts to fool trained object detectors using appended adversarial patches, this new form of attack is mapped into the 3D object world and back-propagated to the texture atlas through differentiable rendering. As such, the adversarial patch is trained under deformation consistent with real-world materials. In addition, and unlike existing adversarial patches, our new 3D adversarial patch is shown to fool state-of-the-art deep object detectors robustly under varying views, potentially leading to an attacking scheme that is persistently strong in the physical world.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 22 Apr 2021.

Builds on

30 of 42 references.

References · 30

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015Fast R-CNNcited by 2,930
  6. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  8. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  9. 2017Adversarial Patchcited by 514
  10. 2017Neural 3D Mesh Renderercited by 437
  11. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  12. 2017Learning from Synthetic Humanscited by 358
18 more
  1. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  2. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  3. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  4. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  5. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  6. 2018Physical Adversarial Examples for Object Detectorscited by 163
  7. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  8. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  9. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  10. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  11. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  12. 2019Model Compression with Adversarial Robustness: A Unified Optimization Frameworkcited by 71
  13. 2017Adversarial Attacks Beyond the Image Spacecited by 67
  14. 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
  15. 2020Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inferencecited by 45
  16. 2018RenderNet: A deep convolutional network for differentiable rendering from 3D shapescited by 42
  17. 2019Physical Adversarial Textures that Fool Visual Object Trackingcited by 30
  18. 2019Adversarial T-shirt! Evading Person Detectors in A Physical Worldcited by 13

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 2; 2025: 1.

8 papers.

  1. 2024Object Detectors in the Open Environment: Challenges, Solutions, and Outlookcited by 13
  2. 2021Two-Face: Adversarial Audit of Commercial Face Recognition Systemscited by 8
  3. 2022Transferable Physical Attack against Object Detection with Separable Attentioncited by 6
  4. 2023Exploring the Physical World Adversarial Robustness of Vehicle Detectioncited by 5
  5. 2025AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systemscited by 4
  6. 2024RenderBender: A Survey on Adversarial Attacks Using Differentiable Renderingcited by 3
  7. 2023Fool the Hydra: Adversarial Attacks against Multi-view Object Detection Systemscited by 1
  8. 2023Physical Adversarial Examples for Multi-Camera Systemscited by 0