mlsanityData to 7 Oct 2026

Embedding Watermarks into Deep Neural Networks

arXiv 1701.04082 ↗First posted 15 Jan 2017cs.CVcited by 227

Not on the map. Why?

Cited by 67 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is necessary to protect the rights of shared trained models. To this end, we propose to use a digital watermarking technology to protect intellectual property or detect intellectual property infringement of trained models. Firstly, we formulate a new problem: embedding watermarks into deep neural networks. We also define requirements, embedding situations, and attack types for watermarking to deep neural networks. Secondly, we propose a general framework to embed a watermark into model parameters using a parameter regularizer. Our approach does not hurt the performance of networks into which a watermark is embedded. Finally, we perform comprehensive experiments to reveal the potential of watermarking to deep neural networks as a basis of this new problem. We show that our framework can embed a watermark in the situations of training a network from scratch, fine-tuning, and distilling without hurting the performance of a deep neural network. The embedded watermark does not disappear even after fine-tuning or parameter pruning; the watermark completely remains even after removing 65% of parameters were pruned. The implementation of this research is: https://github.com/yu4u/dnn-watermark

Key facts. Cited by 227 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 44; 2023: 52; 2024: 43; 2025: 29; 2026: 21.

227 papers.

Sort:

By area:

  1. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  2. 2023Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robustcited by 179
  3. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  4. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 115
  5. 2023A Survey of Text Watermarking in the Era of Large Language Modelscited by 102
  6. 2021Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratchcited by 98
  7. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87
  8. 2021Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Modelscited by 78
  9. 2021Protecting Intellectual Property of Language Generation APIs with Lexical Watermarkcited by 78
  10. 2023Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Modelscited by 77
  11. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
  12. 2022Membership Inference Attacks Against Text-to-image Generation Modelscited by 66
38 more
  1. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermarkcited by 61
  2. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  3. 2021Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorizationcited by 50
  4. 2023Leveraging Optimization for Adaptive Attacks on Image Watermarkscited by 50
  5. 2021Deep Model Intellectual Property Protection via Deep Watermarkingcited by 47
  6. 2021Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attackcited by 45
  7. 2022Watermarking Pre-trained Language Models with Backdooringcited by 44
  8. 2022SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoderscited by 43
  9. 2022VeriFi: Towards Verifiable Federated Unlearningcited by 41
  10. 2022Certified Neural Network Watermarks with Randomized Smoothingcited by 39
  11. 2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 39
  12. 2021Undistillable: Making A Nasty Teacher That CANNOT teach studentscited by 36
  13. 2021Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Releasecited by 35
  14. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  15. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  16. 2023Watermarking Diffusion Modelcited by 34
  17. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 34
  18. 2021ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detectioncited by 33
  19. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 33
  20. 2023HuRef: HUman-REadable Fingerprint for Large Language Modelscited by 32
  21. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  22. 2022Distillation-Resistant Watermarking for Model Protection in NLPcited by 29
  23. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 27
  24. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  25. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 25
  26. 2022Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networkscited by 21
  27. 2023Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscationcited by 20
  28. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  29. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  30. 2021Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authenticationcited by 17
  31. 2023False Claims against Model Ownership Resolutioncited by 17
  32. 2023Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Processcited by 17
  33. 2021You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownershipcited by 16
  34. 2023GrOVe: Ownership Verification of Graph Neural Networks using Embeddingscited by 16
  35. 2024MEA-Defender: A Robust Watermark against Model Extraction Attackcited by 16
  36. 2021A Protection Method of Trained CNN Model with Secret Key from Unauthorized Accesscited by 15
  37. 2024ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Modelscited by 15
  38. 2022On the Exploitation of Deepfake Model Recognitioncited by 14

50 most cited of 227 All 227 (JSON)