mlsanityData to 7 Oct 2026

Optical Adversarial Attack

arXiv 2108.06247 ↗First posted 13 Aug 2021cs.AIcited by 43

Not on the map. Why?

Abstract (arXiv)

We introduce OPtical ADversarial attack (OPAD). OPAD is an adversarial attack in the physical space aiming to fool image classifiers without physically touching the objects (e.g., moving or painting the objects). The principle of OPAD is to use structured illumination to alter the appearance of the target objects. The system consists of a low-cost projector, a camera, and a computer. The challenge of the problem is the non-linearity of the radiometric response of the projector and the spatially varying spectral response of the scene. Attacks generated in a conventional approach do not work in this setting unless they are calibrated to compensate for such a projector-camera model. The proposed solution incorporates the projector-camera model into the adversarial attack optimization, where a new attack formulation is derived. Experimental results prove the validity of the solution. It is demonstrated that OPAD can optically attack a real 3D object in the presence of background lighting for white-box, black-box, targeted, and untargeted attacks. Theoretical analysis is presented to quantify the fundamental performance limit of the system.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 13 Aug 2021.

Builds on

25 of 34 references.

References · 25

  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. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  9. 2016Universal adversarial perturbationscited by 774
  10. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  11. 2017Detecting Adversarial Samples from Artifactscited by 244
  12. 2017On Detecting Adversarial Perturbationscited by 232
13 more
  1. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  2. 2018Physical Adversarial Examples for Object Detectorscited by 163
  3. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  4. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  5. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  6. 2017SafetyNet: Detecting and Rejecting Adversarial Examples Robustlycited by 76
  7. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  8. 2019Adversarial Objects Against LiDAR-Based Autonomous Driving Systemscited by 62
  9. 2015Adversarial Manipulation of Deep Representationscited by 56
  10. 2020Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Studycited by 40
  11. 2019Fooling a Real Car with Adversarial Traffic Signscited by 29
  12. 2018Projecting Trouble: Light Based Adversarial Attacks on Deep Learning Classifierscited by 9
  13. 2019CompenNet++: End-to-end Full Projector Compensationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 14; 2023: 12; 2024: 7; 2025: 6; 2026: 4.

43 papers.

Sort:

By area:

  1. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
  2. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  3. 2023Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modelingcited by 41
  4. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 24
  5. 2022Physical-World Optical Adversarial Attacks on 3D Face Recognitioncited by 23
  6. 2023RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical Worldcited by 23
  7. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  8. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  9. 2023Towards more Practical Threat Models in Artificial Intelligence Securitycited by 17
  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
31 more
  1. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  2. 2024Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifierscited by 10
  3. 2023AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systemscited by 8
  4. 2023State-of-the-art optical-based physical adversarial attacks for deep learning computer vision systemscited by 8
  5. 2023Adversarial Attack with Raindropscited by 7
  6. 2022Adversarial Neon Beam: A Light-based Physical Attack to DNNscited by 6
  7. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  8. 2022Adversarial Zoom Lens: A Novel Physical-World Attack to DNNscited by 4
  9. 2024Attack Anything: Blind DNNs via Universal Background Adversarial Attackcited by 3
  10. 2023Fooling Polarization-based Vision using Locally Controllable Polarizing Projectioncited by 2
  11. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  12. 2024Discrete Randomized Smoothing Meets Quantum Computingcited by 2
  13. 2022A Human-in-the-Middle Attack against Object Detection Systemscited by 1
  14. 2022Shadows Aren't So Dangerous After All: A Fast and Robust Defense Against Shadow-Based Adversarial Attackscited by 1
  15. 2022Adversarial Color Projection: A Projector-based Physical Attack to DNNscited by 1
  16. 2022Adversarial Catoptric Light: An Effective, Stealthy and Robust Physical-World Attack to DNNscited by 1
  17. 2024Data Poisoning: An Overlooked Threat to Power Grid Resiliencecited by 1
  18. 2025A Survey of Adversarial Defenses in Vision-based Systems: Categorization, Methods and Challengescited by 1
  19. 2025Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarioscited by 1
  20. 2022Adversarial attacks on an optical neural networkcited by 0
  21. 2023Adversarial Camera Patch: An Effective and Robust Physical-World Attack on Object Detectorscited by 0
  22. 2024Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectorscited by 0
  23. 2024Transient Adversarial 3D Projection Attacks on Object Detection in Autonomous Drivingcited by 0
  24. 2025Device-aware Optical Adversarial Attack for a Portable Projector-camera Systemcited by 0
  25. 2025Adversarial Wear and Tear: Exploiting Natural Damage for Generating Physical-World Adversarial Examplescited by 0
  26. 2025CAPAA: Classifier-Agnostic Projector-Based Adversarial Attackcited by 0
  27. 2025Attack on a PUF-based Secure Binary Neural Networkcited by 0
  28. 2026Rectifying Adversarial Examples Using Their Vulnerabilitiescited by 0
  29. 2026Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attackscited by 0
  30. 2026Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applicationscited by 0
  31. 2026Physically Real-time Infrared Attack against Optical Flow Estimation Networkscited by 0