mlsanityData to 7 Oct 2026

Fooling thermal infrared pedestrian detectors in real world using small bulbs

arXiv 2101.08154 ↗First posted 20 Jan 2021cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

Thermal infrared detection systems play an important role in many areas such as night security, autonomous driving, and body temperature detection. They have the unique advantages of passive imaging, temperature sensitivity and penetration. But the security of these systems themselves has not been fully explored, which poses risks in applying these systems. We propose a physical attack method with small bulbs on a board against the state of-the-art pedestrian detectors. Our goal is to make infrared pedestrian detectors unable to detect real-world pedestrians. Towards this goal, we first showed that it is possible to use two kinds of patches to attack the infrared pedestrian detector based on YOLOv3. The average precision (AP) dropped by 64.12% in the digital world, while a blank board with the same size caused the AP to drop by 29.69% only. After that, we designed and manufactured a physical board and successfully attacked YOLOv3 in the real world. In recorded videos, the physical board caused AP of the target detector to drop by 34.48%, while a blank board with the same size caused the AP to drop by 14.91% only. With the ensemble attack techniques, the designed physical board had good transferability to unseen detectors. We also proposed the first physical multispectral (infrared and visible) attack. By using a combination method, we successfully hide from the visible light and infrared object detection systems at the same time.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 20 Jan 2021.

Builds on

16 of 30 references.

References · 16

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2018YOLOv3: An Incremental Improvementcited by 2,652
  7. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2016Universal adversarial perturbationscited by 774
  11. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  12. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
4 more
  1. 2018Invisible Mask: Practical Attacks on Face Recognition with Infraredcited by 33
  2. 2019Adversarial T-shirt! Evading Person Detectors in A Physical Worldcited by 13
  3. 2020End-to-End Face Parsing via Interlinked Convolutional Neural Networkscited by 6
  4. 2016Linear Support Tensor Machine: Pedestrian Detection in Thermal Infrared Imagescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 18; 2024: 10; 2025: 6; 2026: 7.

51 papers.

Sort:

By area:

  1. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  2. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  3. 2023X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detectioncited by 58
  4. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  5. 2023Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modelingcited by 41
  6. 2023Physically Adversarial Infrared Patches with Learnable Shapes and Locationscited by 38
  7. 2022HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Designcited by 27
  8. 2023Unified Adversarial Patch for Cross-modal Attacks in the Physical Worldcited by 27
  9. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  10. 2023Language-Driven Anchors for Zero-Shot Adversarial Robustnesscited by 23
  11. 2022SoK: On the Semantic AI Security in Autonomous Drivingcited by 22
  12. 2024SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environmentscited by 22
38 more
  1. 2023Unified Adversarial Patch for Visible-Infrared Cross-modal Attacks in the Physical Worldcited by 21
  2. 2022Defensive Patches for Robust Recognition in the Physical Worldcited by 20
  3. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  4. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  5. 2023Physical Adversarial Attacks for Surveillance: A Surveycited by 15
  6. 2023On the Importance of Backbone to the Adversarial Robustness of Object Detectorscited by 12
  7. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  8. 2023Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical Worldcited by 11
  9. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  10. 2023Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical Worldcited by 10
  11. 2023State-of-the-art optical-based physical adversarial attacks for deep learning computer vision systemscited by 8
  12. 2024Infrared Adversarial Car Stickerscited by 8
  13. 2023CBA: Contextual Background Attack against Optical Aerial Detection in the Physical Worldcited by 7
  14. 2022Adversarial Neon Beam: A Light-based Physical Attack to DNNscited by 6
  15. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  16. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  17. 2024Real-world Adversarial Defense against Patch Attacks based on Diffusion Modelcited by 5
  18. 2025Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approachcited by 5
  19. 2023Defending Against Physical Adversarial Patch Attacks on Infrared Human Detectioncited by 4
  20. 2023Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical worldcited by 4
  21. 2024Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical Worldcited by 4
  22. 2024BadPatch: Diffusion-Based Generation of Physical Adversarial Patchescited by 4
  23. 2024Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectorscited by 3
  24. 2024Physics-Based Adversarial Attack on Near-Infrared Human Detector for Nighttime Surveillance Camera Systemscited by 3
  25. 2024Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Gridcited by 1
  26. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  27. 2025Learning Fourier shapes to probe the geometric world of deep neural networkscited by 1
  28. 2026Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modelingcited by 1
  29. 2026Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Patterncited by 1
  30. 2024Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectorscited by 0
  31. 2024PADetBench: Towards Benchmarking Physical Attacks against Object Detectioncited by 0
  32. 2025Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical Worldcited by 0
  33. 2025A Privacy Enhancing Technique to Evade Detection by Street Video Cameras Without Using Adversarial Accessoriescited by 0
  34. 2025Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Modelscited by 0
  35. 2026Thermal Topology Collapse: Universal Physical Patch Attacks on Infrared Vision Systemscited by 0
  36. 2026Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasioncited by 0
  37. 2026Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detectioncited by 0
  38. 2026Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modelingcited by 0

50 most cited of 51 All 51 (JSON)