mlsanityData to 14 Oct 2026

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

arXiv 2404.04956 ↗First posted 7 Apr 2024cs.CV cs.CRcited by 142

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

also in 1 more
Abstract (arXiv)

Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. However, existing methods often compromise the model performance or require additional training, which is undesirable for operators and users. To address this issue, we propose Gaussian Shading, a diffusion model watermarking technique that is both performance-lossless and training-free, while serving the dual purpose of copyright protection and tracing of offending content. Our watermark embedding is free of model parameter modifications and thus is plug-and-play. We map the watermark to latent representations following a standard Gaussian distribution, which is indistinguishable from latent representations obtained from the non-watermarked diffusion model. Therefore we can achieve watermark embedding with lossless performance, for which we also provide theoretical proof. Furthermore, since the watermark is intricately linked with image semantics, it exhibits resilience to lossy processing and erasure attempts. The watermark can be extracted by Denoising Diffusion Implicit Models (DDIM) inversion and inverse sampling. We evaluate Gaussian Shading on multiple versions of Stable Diffusion, and the results demonstrate that Gaussian Shading not only is performance-lossless but also outperforms existing methods in terms of robustness.

Key facts. Cited by 142 papers in the map (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 15 of its 19 references that are in the map. First posted on arXiv 7 Apr 2024.

Builds on

15 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust31 May
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar

Other references · 13

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  7. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  8. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  9. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 532
  10. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Modelscited by 450
  11. 2018HiDDeN: Hiding Data With Deep Networkscited by 397
  12. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 201
1 more
  1. 2019Robust Invisible Video Watermarking with Attentioncited by 149

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 20; 2025: 52; 2026: 70.

142 papers.

Sort:

By area:

  1. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 110
  2. 2024An Undetectable Watermark for Generative Image Modelscited by 81
  3. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Modelscited by 52
  4. 2024SoK: Watermarking for AI-Generated Contentcited by 51
  5. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 50
  6. 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarkingcited by 34
  7. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Modelscited by 31
  8. 2025SynthID-Image: Image watermarking at internet scalecited by 31
  9. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Imagescited by 21
  10. 2025GaussMarker: Robust Dual-Domain Watermark for Diffusion Modelscited by 16
  11. 2025Watermarking Autoregressive Image Generationcited by 16
  12. 2025SEAL: Semantic Aware Image Watermarkingcited by 15
38 more
  1. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 15
  2. 2024SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AIcited by 14
  3. 2025Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integritycited by 14
  4. 2025Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Imagecited by 13
  5. 2025Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarkingcited by 11
  6. 2024Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?cited by 10
  7. 2025Watermarking Diffusion Language Modelscited by 10
  8. 2025On the Difficulty of Constructing a Robust and Publicly-Detectable Watermarkcited by 9
  9. 2026Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injectioncited by 8
  10. 2024AI-generated Image Detection: Passive or Watermark?cited by 7
  11. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Priorcited by 7
  12. 2025TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivitycited by 7
  13. 2025Removal Attack and Defense on AI-generated Content Latent-based Watermarkingcited by 7
  14. 2025Geometric Image Synchronization with Deep Watermarkingcited by 7
  15. 2026SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarkingcited by 7
  16. 2024FoldMark: Protecting Protein Generative Models with Watermarkingcited by 6
  17. 2025WMCopier: Forging Invisible Image Watermarks on Arbitrary Imagescited by 6
  18. 2025NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Modelscited by 6
  19. 2024MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retrainingcited by 5
  20. 2025Video Signature: Implicit Watermarking for Video Diffusion Modelscited by 5
  21. 2025A Watermark for Auto-Regressive Image Generation Modelscited by 5
  22. 2025AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstructioncited by 5
  23. 2025MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Modelscited by 5
  24. 2025Guidance Watermarking for Diffusion Modelscited by 5
  25. 2025Secure and Robust Watermarking for AI-generated Images: A Comprehensive Surveycited by 5
  26. 2026TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectoriescited by 5
  27. 2024The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attackscited by 4
  28. 2024SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolutioncited by 4
  29. 2025Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarioscited by 4
  30. 2025GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Modelcited by 4
  31. 2025A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarkscited by 4
  32. 2025Mitigating Watermark Forgery in Generative Models via Randomized Key Selectioncited by 4
  33. 2025ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generationcited by 4
  34. 2026SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attackscited by 4
  35. 2026MarkSweep: A No-box Removal Attack on AI-Generated Image Watermarking via Noise Intensification and Frequency-aware Denoisingcited by 4
  36. 2026SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermarkcited by 4
  37. 2024Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganographycited by 3
  38. 2025Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Modelscited by 3

50 most cited of 142 All 142 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models
  2. 2026Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models
  3. 2026When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editing
  4. 2026RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction
  5. 2025T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models
  6. 2025Image Watermarking of Generative Diffusion Models
  7. 2024DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion Model
  8. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking