mlsanityData to 14 Oct 2026

State-of-the-art optical-based physical adversarial attacks for deep learning computer vision systems

arXiv 2303.12249 ↗First posted 22 Mar 2023cs.CV cs.CR eess.IVcited by 8

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the computer vision systems based on deep learning. Physical adversarial attacks, which is more realistic, as the perturbation is introduced to the input before it is being captured and converted to a binary image inside the vision system, when compared to digital adversarial attacks. In this paper, we focus on physical adversarial attacks and further classify them into invasive and non-invasive. Optical-based physical adversarial attack techniques (e.g. using light irradiation) belong to the non-invasive category. As the perturbations can be easily ignored by humans as the perturbations are very similar to the effects generated by a natural environment in the real world. They are highly invisibility and executable and can pose a significant or even lethal threats to real systems. This paper focuses on optical-based physical adversarial attack techniques for computer vision systems, with emphasis on the introduction and discussion of optical-based physical adversarial attack techniques.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

36 of 58 references.

References · 36

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  7. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  8. 2017One pixel attack for fooling deep neural networkscited by 582
  9. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  10. 2021End-to-end Interpretable Neural Motion Plannercited by 242
  11. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  12. 2022Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenoncited by 101
24 more
  1. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 97
  2. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  3. 2020Towards Robust LiDAR-based Perception in Autonomous Driving: General Black-box Adversarial Sensor Attack and Countermeasurescited by 95
  4. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 93
  5. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  6. 2021Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blinkcited by 75
  7. 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 70
  8. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  9. 2018Adversarial Examples: Opportunities and Challengescited by 63
  10. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  11. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  12. 2020SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbationscited by 50
  13. 2021Optical Adversarial Attackcited by 43
  14. 2020Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Studycited by 40
  15. 2020Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effectcited by 40
  16. 2020Over-the-Air Adversarial Flickering Attacks against Video Recognition Networkscited by 36
  17. 2018Invisible Mask: Practical Attacks on Face Recognition with Infraredcited by 33
  18. 2017Intriguing Properties of Adversarial Examplescited by 20
  19. 2020SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifierscited by 17
  20. 2021They See Me Rollin': Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensorscited by 17
  21. 2021Adversarial Imaging Pipelinescited by 15
  22. 2022Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNscited by 11
  23. 2018Projecting Trouble: Light Based Adversarial Attacks on Deep Learning Classifierscited by 9
  24. 2022Adversarial Zoom Lens: A Novel Physical-World Attack to DNNscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 2; 2026: 1.

8 papers.

  1. 2023Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlookcited by 20
  2. 2024Black-box Adversarial Attacks Against Image Quality Assessment Modelscited by 8
  3. 2024A Survey on Physical Adversarial Attacks against Face Recognition Systemscited by 4
  4. 2025AdvReal: Physical Adversarial Patch Generation Framework for Security Evaluation of Object Detection Systemscited by 4
  5. 2023Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulationcited by 1
  6. 2023Adversarial sample generation and training using geometric masks for accurate and resilient license plate character recognitioncited by 1
  7. 2025CAPAA: Classifier-Agnostic Projector-Based Adversarial Attackcited by 0
  8. 2026Physical Adversarial Attacks on AI Surveillance Systems:Detection, Tracking, and Visible--Infrared Evasioncited by 0