mlsanityData to 14 Oct 2026

Do GANs leave artificial fingerprints?

arXiv 1812.11842 ↗First posted 31 Dec 2018cs.CVcited by 190

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In the last few years, generative adversarial networks (GAN) have shown tremendous potential for a number of applications in computer vision and related fields. With the current pace of progress, it is a sure bet they will soon be able to generate high-quality images and videos, virtually indistinguishable from real ones. Unfortunately, realistic GAN-generated images pose serious threats to security, to begin with a possible flood of fake multimedia, and multimedia forensic countermeasures are in urgent need. In this work, we show that each GAN leaves its specific fingerprint in the images it generates, just like real-world cameras mark acquired images with traces of their photo-response non-uniformity pattern. Source identification experiments with several popular GANs show such fingerprints to represent a precious asset for forensic analyses.

Key facts. Cited by 190 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 31; 2023: 35; 2024: 44; 2025: 33; 2026: 25.

190 papers.

Sort:

By area:

  1. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
  3. 2022On the detection of synthetic images generated by diffusion modelscited by 283
  4. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 182
  5. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
  6. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  7. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  8. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 123
  9. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  10. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 89
  11. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  12. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
38 more
  1. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  2. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  3. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  4. 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detectioncited by 60
  5. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 59
  6. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  7. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  8. 2024Real-Time Deepfake Detection in the Real-Worldcited by 51
  9. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  10. 2021Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Facescited by 48
  11. 2022Deepfake Network Architecture Attributioncited by 47
  12. 2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
  13. 2023Evaluating Data Attribution for Text-to-Image Modelscited by 45
  14. 2024D3: Scaling Up Deepfake Detection by Learning from Discrepancycited by 45
  15. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  16. 2023Honesty Is the Best Policy: Defining and Mitigating AI Deceptioncited by 40
  17. 2022RepMix: Representation Mixing for Robust Attribution of Synthesized Imagescited by 39
  18. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 37
  19. 2023ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detectioncited by 35
  20. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  21. 2024WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detectioncited by 31
  22. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  23. 2023Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysiscited by 30
  24. 2021Robust Attentive Deep Neural Network for Exposing GAN-generated Facescited by 28
  25. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 28
  26. 2021Towards Universal GAN Image Detectioncited by 26
  27. 2021Wavelet-Packets for Deepfake Image Analysis and Detectioncited by 25
  28. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  29. 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
  30. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 24
  31. 2024Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learningcited by 23
  32. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  33. 2023A Representative Study on Human Detection of Artificially Generated Media Across Countriescited by 22
  34. 2024Beyond Deepfake Images: Detecting AI-Generated Videoscited by 22
  35. 2024Mixture of Low-rank Experts for Transferable AI-Generated Image Detectioncited by 21
  36. 2021Learning to Disentangle GAN Fingerprint for Fake Image Attributioncited by 20
  37. 2024ManiFPT: Defining and Analyzing Fingerprints of Generative Modelscited by 18
  38. 2022Model Attribution of Face-swap Deepfake Videoscited by 17

50 most cited of 190 All 190 (JSON)