mlsanityData to 7 Oct 2026

A survey of deep neural network watermarking techniques

arXiv 2103.09274 ↗First posted 16 Mar 2021cs.CRcited by 69

Not on the map. Why?

Cited by 23 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Protecting the Intellectual Property Rights (IPR) associated to Deep Neural Networks (DNNs) is a pressing need pushed by the high costs required to train such networks and the importance that DNNs are gaining in our society. Following its use for Multimedia (MM) IPR protection, digital watermarking has recently been considered as a mean to protect the IPR of DNNs. While DNN watermarking inherits some basic concepts and methods from MM watermarking, there are significant differences between the two application areas, calling for the adaptation of media watermarking techniques to the DNN scenario and the development of completely new methods. In this paper, we overview the most recent advances in DNN watermarking, by paying attention to cast it into the bulk of watermarking theory developed during the last two decades, while at the same time highlighting the new challenges and opportunities characterizing DNN watermarking. Rather than trying to present a comprehensive description of all the methods proposed so far, we introduce a new taxonomy of DNN watermarking and present a few exemplary methods belonging to each class. We hope that this paper will inspire new research in this exciting area and will help researchers to focus on the most innovative and challenging problems in the field.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 7; 2023: 18; 2024: 21; 2025: 17; 2026: 3.

69 papers.

Sort:

By area:

  1. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  2. 2022Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalizationcited by 97
  3. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  4. 2024SoK: Watermarking for AI-Generated Contentcited by 43
  5. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  6. 2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 39
  7. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Modelscited by 26
  8. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  9. 2024WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrightscited by 25
  10. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  11. 2023False Claims against Model Ownership Resolutioncited by 17
  12. 2023Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Processcited by 17
38 more
  1. 2024GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesiscited by 17
  2. 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 13
  3. 2024Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarkingcited by 11
  4. 2023Wide Flat Minimum Watermarking for Robust Ownership Verification of GANscited by 10
  5. 2024Does Your Neural Code Completion Model Use My Code? A Membership Inference Approachcited by 9
  6. 2024Probabilistically Robust Watermarking of Neural Networkscited by 7
  7. 2025SoK: How Robust is Audio Watermarking in Generative AI models?cited by 7
  8. 2021FooBaR: Fault Fooling Backdoor Attack on Neural Network Trainingcited by 6
  9. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 6
  10. 2023Robust Retraining-free GAN Fingerprinting via Personalized Normalizationcited by 6
  11. 2024Box-Free Model Watermarks Are Prone to Black-Box Removal Attackscited by 6
  12. 2024Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermarkcited by 4
  13. 2025StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Modelscited by 4
  14. 2022TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Codingcited by 3
  15. 2022TinyMLOps: Operational Challenges for Widespread Edge AI Adoptioncited by 3
  16. 2023Hey That's Mine Imperceptible Watermarks are Preserved in Diffusion Generated Outputscited by 3
  17. 2023Safe and Robust Watermark Injection with a Single OoD Imagecited by 3
  18. 2024GENIE: Watermarking Graph Neural Networks for Link Predictioncited by 3
  19. 2024METR: Image Watermarking with Large Number of Unique Messagescited by 3
  20. 2024Towards Data Governance of Frontier AI Modelscited by 3
  21. 2025Innamark: A Whitespace Replacement Information-Hiding Methodcited by 3
  22. 2025Deep Learning-based Dual Watermarking for Image Copyright Protection and Authenticationcited by 3
  23. 2023A Brief Yet In-Depth Survey of Deep Learning-Based Image Watermarkingcited by 2
  24. 2025Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluationcited by 2
  25. 2025Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarkingcited by 2
  26. 2022FBI: Fingerprinting models with Benign Inputscited by 1
  27. 2023Reversible Quantization Index Modulation for Static Deep Neural Network Watermarkingcited by 1
  28. 2023Information Forensics and Security: A quarter-century-long journeycited by 1
  29. 2023Find the Lady: Permutation and Re-Synchronization of Deep Neural Networkscited by 1
  30. 2024A Survey of Fragile Model Watermarkingcited by 1
  31. 2024An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weightingcited by 1
  32. 2025Your Text Encoder Can Be An Object-Level Watermarking Controllercited by 1
  33. 2025ChainMarks: Securing DNN Watermark with Cryptographic Chaincited by 1
  34. 2025Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulationcited by 1
  35. 2025Staining and locking computer vision models without retrainingcited by 1
  36. 2025Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary sizecited by 1
  37. 2025Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarkingcited by 1
  38. 2026Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removalcited by 1

50 most cited of 69 All 69 (JSON)