mlsanityData to 7 Oct 2026

The Stable Signature: Rooting Watermarks in Latent Diffusion Models

arXiv 2303.15435 ↗First posted 27 Mar 2023cs.CV cs.AIcited by 289

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

Generative image modeling enables a wide range of applications but raises ethical concerns about responsible deployment. This paper introduces an active strategy combining image watermarking and Latent Diffusion Models. The goal is for all generated images to conceal an invisible watermark allowing for future detection and/or identification. The method quickly fine-tunes the latent decoder of the image generator, conditioned on a binary signature. A pre-trained watermark extractor recovers the hidden signature from any generated image and a statistical test then determines whether it comes from the generative model. We evaluate the invisibility and robustness of the watermarks on a variety of generation tasks, showing that Stable Signature works even after the images are modified. For instance, it detects the origin of an image generated from a text prompt, then cropped to keep 10% of the content, with 90+% accuracy at a false positive rate below 10-6.

Key facts. Cited by 289 papers in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 82 of its 106 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

82 of 106 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Adversarial purification with Score-based generative models11 Jun

Other references · 81

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  10. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  11. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  12. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
38 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  12. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  13. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  14. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  15. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  16. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  17. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  18. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  19. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  20. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  21. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  22. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  23. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  24. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  25. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  26. 2018Variational image compression with a scale hyperpriorcited by 910
  27. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  28. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  29. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  30. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
  31. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  32. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  33. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  34. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  35. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  36. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  37. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  38. 2021Multi-attentional Deepfake Detectioncited by 339

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 27; 2024: 87; 2025: 87; 2026: 88.

289 papers.

Sort:

By area:

  1. 2023Self-Consuming Generative Models Go MADcited by 239
  2. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robustcited by 179
  3. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Modelscited by 131
  4. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 124
  5. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  6. 2023Audiobox: Unified Audio Generation with Natural Language Promptscited by 120
  7. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 109
  8. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  9. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  10. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 89
  11. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  12. 2023Three Bricks to Consolidate Watermarks for Large Language Modelscited by 80
38 more
  1. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  2. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  3. 2024An Undetectable Watermark for Generative Image Modelscited by 74
  4. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  5. 2024Proactive Detection of Voice Cloning with Localized Watermarkingcited by 67
  6. 2024R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Modelcited by 56
  7. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  8. 2023Advancing Beyond Identification: Multi-bit Watermark for Large Language Modelscited by 51
  9. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 50
  10. 2024Watermark Anything with Localized Messagescited by 49
  11. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Modelscited by 48
  12. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimizationcited by 45
  13. 2024Video Seal: Open and Efficient Video Watermarkingcited by 45
  14. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 43
  15. 2024SoK: Watermarking for AI-Generated Contentcited by 43
  16. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRAcited by 42
  17. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
  18. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  19. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  20. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 34
  21. 2024A Watermark-Conditioned Diffusion Model for IP Protectioncited by 34
  22. 2024Attack-Resilient Image Watermarking Using Stable Diffusioncited by 33
  23. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 29
  24. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  25. 2024A Transfer Attack to Image Watermarkscited by 26
  26. 2024GS-Hider: Hiding Messages into 3D Gaussian Splattingcited by 26
  27. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Modelscited by 26
  28. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  29. 2024WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrightscited by 25
  30. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  31. 2025Generating Multi-Image Synthetic Data for Text-to-Image Customizationcited by 25
  32. 2023ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generationscited by 24
  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. 2024DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Modelcited by 21
  36. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  37. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Spacecited by 19
  38. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 19

50 most cited of 289 All 289 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Image Watermarking of Generative Diffusion Models
  2. 2025TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
  3. 2025MaXsive: High-Capacity and Robust Training-Free Generative Image Watermarking in Diffusion Models
  4. 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage
  5. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks
  6. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarking
  7. 2023A Recipe for Watermarking Diffusion Models
  8. 2025Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models