mlsanityData to 7 Oct 2026

Responsible Disclosure of Generative Models Using Scalable Fingerprinting

arXiv 2012.08726 ↗First posted 16 Dec 2020cs.CR cs.CV cs.CYcited by 90

Not on the map. Why?

Abstract (arXiv)

Over the past years, deep generative models have achieved a new level of performance. Generated data has become difficult, if not impossible, to be distinguished from real data. While there are plenty of use cases that benefit from this technology, there are also strong concerns on how this new technology can be misused to generate deep fakes and enable misinformation at scale. Unfortunately, current deep fake detection methods are not sustainable, as the gap between real and fake continues to close. In contrast, our work enables a responsible disclosure of such state-of-the-art generative models, that allows model inventors to fingerprint their models, so that the generated samples containing a fingerprint can be accurately detected and attributed to a source. Our technique achieves this by an efficient and scalable ad-hoc generation of a large population of models with distinct fingerprints. Our recommended operation point uses a 128-bit fingerprint which in principle results in more than 1038 identifiable models. Experiments show that our method fulfills key properties of a fingerprinting mechanism and achieves effectiveness in deep fake detection and attribution. Code and models are available at https://github.com/ningyu1991/ScalableGANFingerprints .

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 4; 2023: 29; 2024: 29; 2025: 15; 2026: 8.

90 papers.

Sort:

By area:

  1. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  2. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  3. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  4. 2023Three Bricks to Consolidate Watermarks for Large Language Modelscited by 80
  5. 2024Proactive Detection of Voice Cloning with Localized Watermarkingcited by 67
  6. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  7. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  8. 2024R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Modelcited by 56
  9. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 54
  10. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  11. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 50
  12. 2024Watermark Anything with Localized Messagescited by 49
38 more
  1. 2022Deepfake Network Architecture Attributioncited by 47
  2. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 46
  3. 2024Video Seal: Open and Efficient Video Watermarkingcited by 45
  4. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  5. 2022RepMix: Representation Mixing for Robust Attribution of Synthesized Imagescited by 39
  6. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  7. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  8. 2024A Watermark-Conditioned Diffusion Model for IP Protectioncited by 34
  9. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  10. 2023Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectivescited by 31
  11. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  12. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  13. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 22
  14. 2024Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detectioncited by 21
  15. 2023Attributing Image Generative Models using Latent Fingerprintscited by 20
  16. 2021Learning to Disentangle GAN Fingerprint for Fake Image Attributioncited by 19
  17. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 19
  18. 2023Robust Identity Perceptual Watermark Against Deepfake Face Swappingcited by 17
  19. 2024GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesiscited by 17
  20. 2023Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?cited by 15
  21. 2024Which Model Generated This Image? A Model-Agnostic Approach for Origin Attributioncited by 15
  22. 2022On the Exploitation of Deepfake Model Recognitioncited by 14
  23. 2024Are CLIP features all you need for Universal Synthetic Image Origin Attribution?cited by 14
  24. 2025From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakescited by 14
  25. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 14
  26. 2021Deep Video Inpainting Detectioncited by 11
  27. 2023EKILA: Synthetic Media Provenance and Attribution for Generative Artcited by 11
  28. 2023Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videoscited by 11
  29. 2023Single-Model Attribution of Generative Models Through Final-Layer Inversioncited by 10
  30. 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
  31. 2023Wide Flat Minimum Watermarking for Robust Ownership Verification of GANscited by 10
  32. 2023GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusionscited by 10
  33. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  34. 2024LVMark: Robust Watermark for Latent Video Diffusion Modelscited by 8
  35. 2023DECORAIT -- DECentralized Opt-in/out Registry for AI Trainingcited by 7
  36. 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Spacecited by 7
  37. 2023VADER: Video Alignment Differencing and Retrievalcited by 6
  38. 2023Collaborative Watermarking for Adversarial Speech Synthesiscited by 6

50 most cited of 90 All 90 (JSON)