mlsanityData to 7 Oct 2026

Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling

arXiv 2307.01778 ↗First posted 4 Jul 2023cs.CV cs.AI cs.CRcited by 41

Not on the map. Why?

Abstract (arXiv)

Recent works have proposed to craft adversarial clothes for evading person detectors, while they are either only effective at limited viewing angles or very conspicuous to humans. We aim to craft adversarial texture for clothes based on 3D modeling, an idea that has been used to craft rigid adversarial objects such as a 3D-printed turtle. Unlike rigid objects, humans and clothes are non-rigid, leading to difficulties in physical realization. In order to craft natural-looking adversarial clothes that can evade person detectors at multiple viewing angles, we propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes, camouflage textures. We leverage the Voronoi diagram and Gumbel-softmax trick to parameterize the camouflage textures and optimize the parameters via 3D modeling. Moreover, we propose an efficient augmentation pipeline on 3D meshes combining topologically plausible projection (TopoProj) and Thin Plate Spline (TPS) to narrow the gap between digital and real-world objects. We printed the developed 3D texture pieces on fabric materials and tailored them into T-shirts and trousers. Experiments show high attack success rates of these clothes against multiple detectors.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 4 Jul 2023.

Builds on

36 of 51 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Mask R-CNNcited by 7,259
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  10. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  11. 2018YOLOv3: An Incremental Improvementcited by 2,652
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
24 more
  1. 2016Adversarial examples in the physical worldcited by 1,762
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  5. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  7. 2017Adversarial Patchcited by 514
  8. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  9. 2018Physical Adversarial Examples for Object Detectorscited by 163
  10. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  11. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  12. 2014A* Samplingcited by 150
  13. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  14. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  15. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
  16. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  17. 2019On Physical Adversarial Patches for Object Detectioncited by 93
  18. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  19. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  20. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  21. 2021Optical Adversarial Attackcited by 43
  22. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  23. 2021Learning Coated Adversarial Camouflages for Object Detectorscited by 17
  24. 2020Can 3D Adversarial Logos Cloak Humans?cited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 13; 2025: 16; 2026: 10.

41 papers.

Sort:

By area:

  1. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  2. 2025Safety of Embodied Navigation: A Surveycited by 9
  3. 2024Infrared Adversarial Car Stickerscited by 8
  4. 2025UV-Attack: Physical-World Adversarial Attacks for Person Detection via Dynamic-NeRF-based UV Mappingcited by 8
  5. 2024Flexible Physical Camouflage Generation Based on a Differential Approachcited by 7
  6. 2024Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigationcited by 6
  7. 20253D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generationcited by 6
  8. 2024I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectorscited by 5
  9. 2025Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approachcited by 5
  10. 2024CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectorscited by 4
  11. 2024DynamicPAE: Generating Scene-Aware Physical Adversarial Examples in Real-Timecited by 4
  12. 2025AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systemscited by 4
29 more
  1. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  2. 2024Attack Anything: Blind DNNs via Universal Background Adversarial Attackcited by 3
  3. 2024RenderBender: A Survey on Adversarial Attacks Using Differentiable Renderingcited by 3
  4. 2024Adversarial Attacks on Hyperbolic Networkscited by 3
  5. 2025PBCAT: Patch-based composite adversarial training against physically realizable attacks on object detectioncited by 3
  6. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  7. 2025Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systemscited by 2
  8. 2026Transferable Physical-World Adversarial Patches Against Pedestrian Detection Modelscited by 2
  9. 2024Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identificationcited by 1
  10. 2024Prompt-Guided Environmentally Consistent Adversarial Patchcited by 1
  11. 2025Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environmentscited by 1
  12. 2025UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attackscited by 1
  13. 2025A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical Worldcited by 1
  14. 2026Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Patterncited by 1
  15. 2023Trainwreck: A damaging adversarial attack on image classifierscited by 0
  16. 2024PADetBench: Towards Benchmarking Physical Attacks against Object Detectioncited by 0
  17. 2025Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical Worldcited by 0
  18. 2025AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patchescited by 0
  19. 2025DisPatch: Disarming Adversarial Patches in Object Detection with Diffusion Modelscited by 0
  20. 2025Physically Realistic Sequence-Level Adversarial Clothing for Robust Human-Detection Evasioncited by 0
  21. 2025Robust Physical Adversarial Patches Using Dynamically Optimized Clusterscited by 0
  22. 2026R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splattingcited by 0
  23. 2026Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decompositioncited by 0
  24. 2026Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detectioncited by 0
  25. 2026AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustnesscited by 0
  26. 2026Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policiescited by 0
  27. 2026VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasioncited by 0
  28. 2026Detectors Learn the Wrong Thing: Shortcut-Resistant Adversarial Training Against Physically Realizable Attackscited by 0
  29. 2026AdvTiles: Physical Adversarial Camouflage Clothing against Person Detectors via Learnable Tilescited by 0