mlsanityData to 7 Oct 2026

Adversarial Neon Beam: A Light-based Physical Attack to DNNs

arXiv 2204.00853 ↗First posted 2 Apr 2022cs.CV cs.CR cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

In the physical world, deep neural networks (DNNs) are impacted by light and shadow, which can have a significant effect on their performance. While stickers have traditionally been used as perturbations in most physical attacks, their perturbations can often be easily detected. To address this, some studies have explored the use of light-based perturbations, such as lasers or projectors, to generate more subtle perturbations, which are artificial rather than natural. In this study, we introduce a novel light-based attack called the adversarial neon beam (AdvNB), which utilizes common neon beams to create a natural black-box physical attack. Our approach is evaluated on three key criteria: effectiveness, stealthiness, and robustness. Quantitative results obtained in simulated environments demonstrate the effectiveness of the proposed method, and in physical scenarios, we achieve an attack success rate of 81.82%, surpassing the baseline. By using common neon beams as perturbations, we enhance the stealthiness of the proposed attack, enabling physical samples to appear more natural. Moreover, we validate the robustness of our approach by successfully attacking advanced DNNs with a success rate of over 75% in all cases. We also discuss defense strategies against the AdvNB attack and put forward other light-based physical attacks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 58 of its 88 references that are in the map. First posted on arXiv 2 Apr 2022.

Builds on

58 of 88 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2015Continuous control with deep reinforcement learningcited by 3,279
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2016Adversarial examples in the physical worldcited by 1,762
38 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  3. 2016Universal adversarial perturbationscited by 774
  4. 2017One pixel attack for fooling deep neural networkscited by 579
  5. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  6. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  7. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  8. 2018Spatially Transformed Adversarial Examplescited by 195
  9. 2018Physical Adversarial Examples for Object Detectorscited by 163
  10. 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 161
  11. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  12. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  13. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  14. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  15. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  16. 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
  17. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  18. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
  19. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  20. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  21. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  22. 2018Semantic Adversarial Examplescited by 86
  23. 2017A General Framework for Adversarial Examples with Objectivescited by 82
  24. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  25. 2021FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attackcited by 74
  26. 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 72
  27. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  28. 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 69
  29. 2017Adversarial Attacks Beyond the Image Spacecited by 67
  30. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  31. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  32. 2022DTA: Physical Camouflage Attacks using Differentiable Transformation Networkcited by 51
  33. 2021Optical Adversarial Attackcited by 43
  34. 2020Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Studycited by 40
  35. 2020Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effectcited by 40
  36. 2022Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Priorcited by 38
  37. 2020GreedyFool: Distortion-Aware Sparse Adversarial Attackcited by 37
  38. 2021TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systemscited by 36

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

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

6 papers.

  1. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  2. 2023Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical Worldcited by 10
  3. 2022Adversarial Zoom Lens: A Novel Physical-World Attack to DNNscited by 4
  4. 2023Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical worldcited by 4
  5. 2024Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectorscited by 0
  6. 2025Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examplescited by 0