mlsanityData to 7 Oct 2026

Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink

arXiv 2103.06504 ↗First posted 11 Mar 2021cs.LG cs.AI cs.CRcited by 75

Not on the map. Why?

Abstract (arXiv)

Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world scenario. In this work, we show by simply using a laser beam that DNNs are easily fooled. To this end, we propose a novel attack method called Adversarial Laser Beam (AdvLB), which enables manipulation of laser beam's physical parameters to perform adversarial attack. Experiments demonstrate the effectiveness of our proposed approach in both digital- and physical-settings. We further empirically analyze the evaluation results and reveal that the proposed laser beam attack may lead to some interesting prediction errors of the state-of-the-art DNNs. We envisage that the proposed AdvLB method enriches the current family of adversarial attacks and builds the foundation for future robustness studies for light.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

22 of 30 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  10. 2017Adversarial Patchcited by 514
  11. 2019Simple Black-box Adversarial Attackscited by 249
  12. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
10 more
  1. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  2. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  3. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  4. 2018Semantic Adversarial Examplescited by 86
  5. 2019Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distancecited by 72
  6. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 70
  7. 2017Adversarial Attacks Beyond the Image Spacecited by 67
  8. 2020Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Studycited by 40
  9. 2018Invisible Mask: Practical Attacks on Face Recognition with Infraredcited by 33
  10. 2019Physical Adversarial Textures that Fool Visual Object Trackingcited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 19; 2023: 20; 2024: 17; 2025: 8; 2026: 6.

75 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
  3. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  4. 2021AdvDrop: Adversarial Attack to DNNs by Dropping Informationcited by 55
  5. 2021Optical Adversarial Attackcited by 43
  6. 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
  7. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  8. 2022Prior-Guided Adversarial Initialization for Fast Adversarial Trainingcited by 34
  9. 2025Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attackscited by 32
  10. 2022HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Designcited by 27
  11. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  12. 2022Physical-World Optical Adversarial Attacks on 3D Face Recognitioncited by 23
38 more
  1. 2023RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical Worldcited by 23
  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. 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
  5. 2022Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defensecited by 14
  6. 2024Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perceptioncited by 14
  7. 2024Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Featurecited by 13
  8. 2024Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspectivecited by 12
  9. 2021RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracycited by 11
  10. 2022Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNscited by 11
  11. 2022Adversarial Color Film: Effective Physical-World Attack to DNNscited by 11
  12. 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
  13. 2023Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical Worldcited by 11
  14. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  15. 2023Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical Worldcited by 10
  16. 2023State-of-the-art optical-based physical adversarial attacks for deep learning computer vision systemscited by 8
  17. 2023Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworkscited by 8
  18. 2024Machine Learning Robustness: A Primercited by 8
  19. 2023Adversarial Attack with Raindropscited by 7
  20. 2022Adversarial Neon Beam: A Light-based Physical Attack to DNNscited by 6
  21. 2024Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspectivecited by 6
  22. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  23. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  24. 2024Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attackscited by 5
  25. 2022Enhancing Transferability of Adversarial Examples with Spatial Momentumcited by 4
  26. 2022Adversarial Zoom Lens: A Novel Physical-World Attack to DNNscited by 4
  27. 2023Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimizationcited by 4
  28. 2023Embodied Laser Attack:Leveraging Scene Priors to Achieve Agent-based Robust Non-contact Attackscited by 4
  29. 2024Secure Traffic Sign Recognition: An Attention-Enabled Universal Image Inpainting Mechanism against Light Patch Attackscited by 4
  30. 2024Learning to See Through Dazzlecited by 3
  31. 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Taskscited by 3
  32. 2024Attack Anything: Blind DNNs via Universal Background Adversarial Attackcited by 3
  33. 2024Physics-Based Adversarial Attack on Near-Infrared Human Detector for Nighttime Surveillance Camera Systemscited by 3
  34. 2022The Weaknesses of Adversarial Camouflage in Overhead Imagerycited by 2
  35. 2023Fooling Polarization-based Vision using Locally Controllable Polarizing Projectioncited by 2
  36. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  37. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  38. 2024The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognitioncited by 2

50 most cited of 75 All 75 (JSON)