mlsanityData to 7 Oct 2026

Distortion Agnostic Deep Watermarking

arXiv 2001.04580 ↗First posted 14 Jan 2020cs.MM cs.CV cs.LGcited by 88

Not on the map. Why?

Cited by 25 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learning-based methods achieved impressive results in both visual quality and message payload under a wide variety of image distortions. However, these methods all require differentiable models for the image distortions at training time, and may generalize poorly to unknown distortions. This is undesirable since the types of distortions applied to watermarked images are usually unknown and non-differentiable. In this paper, we propose a new framework for distortion-agnostic watermarking, where the image distortion is not explicitly modeled during training. Instead, the robustness of our system comes from two sources: adversarial training and channel coding. Compared to training on a fixed set of distortions and noise levels, our method achieves comparable or better results on distortions available during training, and better performance on unknown distortions.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 20; 2024: 18; 2025: 22; 2026: 9.

88 papers.

Sort:

By area:

  1. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  3. 2023Generating Images with Multimodal Language Modelscited by 259
  4. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  5. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 105
  6. 2021Watermarking Images in Self-Supervised Latent Spacescited by 90
  7. 2023AvatarReX: Real-time Expressive Full-body Avatarscited by 83
  8. 2023Robust Multi-bit Natural Language Watermarking through Invariant Featurescited by 76
  9. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  10. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  11. 2023Advancing Beyond Identification: Multi-bit Watermark for Large Language Modelscited by 51
  12. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
38 more
  1. 2024Watermark Anything with Localized Messagescited by 49
  2. 2024Video Seal: Open and Efficient Video Watermarkingcited by 45
  3. 2023SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detectioncited by 43
  4. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  5. 2024Attack-Resilient Image Watermarking Using Stable Diffusioncited by 33
  6. 2023StoryBench: A Multifaceted Benchmark for Continuous Story Visualizationcited by 27
  7. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  8. 2025SynthID-Image: Image watermarking at internet scalecited by 26
  9. 2021TAFIM: Targeted Adversarial Attacks against Facial Image Manipulationscited by 25
  10. 2024WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrightscited by 25
  11. 2021Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderingscited by 23
  12. 2021Data Hiding with Deep Learning: A Survey Unifying Digital Watermarking and Steganographycited by 23
  13. 2022Learning to Immunize Images for Tamper Localization and Self-Recoverycited by 19
  14. 2022FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakescited by 18
  15. 2024GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splattingcited by 18
  16. 2021FaceGuard: Proactive Deepfake Detectioncited by 16
  17. 2023Necessary and Sufficient Watermark for Large Language Modelscited by 16
  18. 2024Stable Signature is Unstable: Removing Image Watermark from Diffusion Modelscited by 16
  19. 2023The Age of Synthetic Realities: Challenges and Opportunitiescited by 15
  20. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  21. 2025Watermarking Autoregressive Image Generationcited by 15
  22. 2025Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integritycited by 14
  23. 2025Pixel Seal: Adversarial-only training for invisible image and video watermarkingcited by 14
  24. 2023Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videoscited by 11
  25. 2025The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fieldscited by 10
  26. 2025Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Modelscited by 10
  27. 2021A Brief Survey on Deep Learning Based Data Hidingcited by 9
  28. 2024Watermark-based Attribution of AI-Generated Contentcited by 8
  29. 2025Geometric Image Synchronization with Deep Watermarkingcited by 7
  30. 2021A Compact Neural Network-based Algorithm for Robust Image Watermarkingcited by 6
  31. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Priorcited by 6
  32. 2023PRIS: Practical robust invertible network for image steganographycited by 5
  33. 2024Social Media Authentication and Combating Deepfakes using Semi-fragile Invisible Image Watermarkingcited by 5
  34. 2022A Robust Document Image Watermarking Scheme using Deep Neural Networkcited by 4
  35. 2024Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blendingcited by 4
  36. 2025Secure and Robust Watermarking for AI-generated Images: A Comprehensive Surveycited by 4
  37. 2021Hiding Images into Images with Real-world Robustnesscited by 3
  38. 2023Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustnesscited by 3

50 most cited of 88 All 88 (JSON)