mlsanityData to 7 Oct 2026

Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data

arXiv 2007.08457 ↗First posted 16 Jul 2020cs.CR cs.CV cs.CYcited by 200

Not on the map. Why?

Cited by 64 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual misinformation. While existing research work on deepfake detection demonstrates high accuracy, it is subject to advances in generation techniques and adversarial iterations on detection countermeasure techniques. Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models. Our approach is simple and effective. We first embed artificial fingerprints into training data, then validate a surprising discovery on the transferability of such fingerprints from training data to generative models, which in turn appears in the generated deepfakes. Experiments show that our fingerprinting solution (1) holds for a variety of cutting-edge generative models, (2) leads to a negligible side effect on generation quality, (3) stays robust against image-level and model-level perturbations, (4) stays hard to be detected by adversaries, and (5) converts deepfake detection and attribution into trivial tasks and outperforms the recent state-of-the-art baselines. Our solution closes the responsibility loop between publishing pre-trained generative model inventions and their possible misuses, which makes it independent of the current arms race. Code and models are available at https://github.com/ningyu1991/ArtificialGANFingerprints .

Key facts. Cited by 200 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 15; 2023: 52; 2024: 57; 2025: 41; 2026: 26.

200 papers.

Sort:

By area:

  1. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  2. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  3. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  4. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  5. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robustcited by 179
  6. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  7. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Modelscited by 131
  8. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  9. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
  10. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  11. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
  12. 2023AI Transparency in the Age of LLMs: A Human-Centered Research Roadmapcited by 119
38 more
  1. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  2. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  3. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  4. 2021Multimodal Conditional Image Synthesis with Product-of-Experts GANscited by 75
  5. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  6. 2024Proactive Detection of Voice Cloning with Localized Watermarkingcited by 67
  7. 2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
  8. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  9. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  10. 2024R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Modelcited by 56
  11. 2023RoSteALS: Robust Steganography using Autoencoder Latent Spacecited by 54
  12. 2022DeepPrivacy2: Towards Realistic Full-Body Anonymizationcited by 51
  13. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  14. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 50
  15. 2024Watermark Anything with Localized Messagescited by 49
  16. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimizationcited by 45
  17. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  18. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
  19. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRAcited by 42
  20. 2023DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Modelscited by 41
  21. 2022RepMix: Representation Mixing for Robust Attribution of Synthesized Imagescited by 39
  22. 2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 39
  23. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  24. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  25. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 34
  26. 2024A Watermark-Conditioned Diffusion Model for IP Protectioncited by 34
  27. 2022StegaNeRF: Embedding Invisible Information within Neural Radiance Fieldscited by 32
  28. 2023Contrastive Pseudo Learning for Open-World DeepFake Attributioncited by 27
  29. 2023Nepotistically Trained Generative-AI Models Collapsecited by 27
  30. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  31. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  32. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  33. 2024Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Modelscited by 22
  34. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  35. 2024InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenancecited by 21
  36. 2024LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarkscited by 21
  37. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  38. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Spacecited by 19

50 most cited of 200 All 200 (JSON)