mlsanityData to 14 Oct 2026

Towards Robust Content Watermarking Against Removal and Forgery Attacks

arXiv 2604.06662 ↗First posted 8 Apr 2026cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Generated contents have raised serious concerns about copyright protection, image provenance, and credit attribution. A potential solution for these problems is watermarking. Recently, content watermarking for text-to-image diffusion models has been studied extensively for its effective detection utility and robustness. However, these watermarking techniques are vulnerable to potential adversarial attacks, such as removal attacks and forgery attacks. In this paper, we build a novel watermarking paradigm called Instance-Specific watermarking with Two-Sided detection (ISTS) to resist removal and forgery attacks. Specifically, we introduce a strategy that dynamically controls the injection time and watermarking patterns based on the semantics of users' prompts. Furthermore, we propose a new two-sided detection approach to enhance robustness in watermark detection. Experiments have demonstrated the superiority of our watermarking against removal and forgery attacks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 58 of its 71 references that are in the map. First posted on arXiv 8 Apr 2026.

Builds on

58 of 71 references.

References · 58

  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. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  10. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  11. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  12. 2023A Watermark for Large Language Modelscited by 725
38 more
  1. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  2. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 477
  3. 2022Diffusion Models for Adversarial Purificationcited by 476
  4. 2023Robust Distortion-free Watermarks for Language Modelscited by 320
  5. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
  6. 2023Provable Robust Watermarking for AI-Generated Textcited by 299
  7. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 265
  8. 2023Undetectable Watermarks for Language Modelscited by 226
  9. 2023On the Reliability of Watermarks for Large Language Modelscited by 189
  10. 2019Robust Invisible Video Watermarking with Attentioncited by 149
  11. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Modelscited by 142
  12. 2023A Recipe for Watermarking Diffusion Modelscited by 141
  13. 2021Adversarial purification with Score-based generative modelscited by 134
  14. 2023Invisible Image Watermarks Are Provably Removable Using Generative AIcited by 134
  15. 2024WAVES: Benchmarking the Robustness of Image Watermarkscited by 97
  16. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 91
  17. 2023Robustness of AI-Image Detectors: Fundamental Limits and Practical Attackscited by 81
  18. 2024An Undetectable Watermark for Generative Image Modelscited by 81
  19. 2023Evading Watermark based Detection of AI-Generated Contentcited by 78
  20. 2024Adaptive Text Watermark for Large Language Modelscited by 67
  21. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 52
  22. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Modelscited by 52
  23. 2024Image Watermarks are Removable Using Controllable Regeneration from Clean Noisecited by 50
  24. 2024Video Seal: Open and Efficient Video Watermarkingcited by 48
  25. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimizationcited by 46
  26. 2024Attack-Resilient Image Watermarking Using Stable Diffusioncited by 35
  27. 2025VideoShield: Regulating Diffusion-based Video Generation Models via Watermarkingcited by 34
  28. 2024A Transfer Attack to Image Watermarkscited by 27
  29. 2024UnMarker: A Universal Attack on Defensive Image Watermarkingcited by 24
  30. 2024Hidden in the Noise: Two-Stage Robust Watermarking for Imagescited by 21
  31. 2024Debiasing Watermarks for Large Language Models via Maximal Couplingcited by 19
  32. 2025VideoMark: A Distortion-Free Robust Watermarking Framework for Video Diffusion Modelscited by 18
  33. 2024De-mark: Watermark Removal in Large Language Modelscited by 14
  34. 2025Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Imagecited by 13
  35. 2025Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Modelscited by 12
  36. 2019Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networkscited by 10
  37. 2024TabularMark: Watermarking Tabular Datasets for Machine Learningcited by 8
  38. 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Spacecited by 8

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecyclecited by 2
  2. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0
  3. 2026On the Intrinsic Limited Robustness of Latent-Based Watermarkingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
  2. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking
  3. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
  4. 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage
  5. 2025Removal Attack and Defense on AI-generated Content Latent-based Watermarking
  6. 2025When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
  7. 2026MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
  8. 2026Persistent Watermarking of Text-to-Image Models