mlsanityData to 14 Oct 2026

Moir'e Attack (MA): A New Potential Risk of Screen Photos

arXiv 2110.10444 ↗First posted 20 Oct 2021cs.CV eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

Images, captured by a camera, play a critical role in training Deep Neural Networks (DNNs). Usually, we assume the images acquired by cameras are consistent with the ones perceived by human eyes. However, due to the different physical mechanisms between human-vision and computer-vision systems, the final perceived images could be very different in some cases, for example shooting on digital monitors. In this paper, we find a special phenomenon in digital image processing, the moir'e effect, that could cause unnoticed security threats to DNNs. Based on it, we propose a Moir'e Attack (MA) that generates the physical-world moir'e pattern adding to the images by mimicking the shooting process of digital devices. Extensive experiments demonstrate that our proposed digital Moir'e Attack (MA) is a perfect camouflage for attackers to tamper with DNNs with a high success rate (100.0% for untargeted and 97.0% for targeted attack with the noise budget ε=4), high transferability rate across different models, and high robustness under various defenses. Furthermore, MA owns great stealthiness because the moir'e effect is unavoidable due to the camera's inner physical structure, which therefore hardly attracts the awareness of humans. Our code is available at https://github.com/Dantong88/MoireAttack.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 20 Oct 2021.

Builds on

34 of 44 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Mask R-CNNcited by 7,277
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  11. 2016Adversarial examples in the physical worldcited by 1,769
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
22 more
  1. 2016Adversarial Machine Learning at Scalecited by 936
  2. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  3. 2017Countering Adversarial Images using Input Transformationscited by 520
  4. 2017Adversarial Patchcited by 517
  5. 2016A study of the effect of JPG compression on adversarial imagescited by 197
  6. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 167
  7. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  8. 2018Adversarial Attacks and Defences Competitioncited by 96
  9. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  10. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  11. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 87
  12. 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
  13. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
  14. 2018Deflecting Adversarial Attacks with Pixel Deflectioncited by 71
  15. 2020A Unified Approach to Interpreting and Boosting Adversarial Transferabilitycited by 71
  16. 2019Curls & Whey: Boosting Black-Box Adversarial Attackscited by 37
  17. 2020Improving Query Efficiency of Black-box Adversarial Attackcited by 34
  18. 2018Moir'e Photo Restoration Using Multiresolution Convolutional Neural Networkscited by 30
  19. 2019Multi-scale Dynamic Feature Encoding Network for Image Demoireingcited by 23
  20. 2019AIM 2019 Challenge on Image Demoireing: Dataset and Studycited by 13
  21. 2020NTIRE 2020 Challenge on Image Demoireing: Methods and Resultscited by 9
  22. 2018Demoir'eing of Camera-Captured Screen Images Using Deep Convolutional Neural Networkcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 2; 2026: 1.

4 papers.

  1. 2022Self-Ensemble Adversarial Training for Improved Robustnesscited by 38
  2. 2025Through the Lens: Benchmarking Deepfake Detectors Against Moir'e-Induced Distortionscited by 1
  3. 2025SIDME: Self-supervised Image Demoir'eing via Masked Encoder-Decoder Reconstructioncited by 0
  4. 2026Illumination-Aware Contactless Fingerprint Spoof Detection via Paired Flash-Non-Flash Imagingcited by 0