mlsanityData to 7 Oct 2026

Robust Watermarking of Neural Network with Exponential Weighting

arXiv 1901.06151 ↗First posted 18 Jan 2019cs.CRcited by 48

Not on the map. Why?

Abstract (arXiv)

Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, we need to treat neural network models as valuable intellectual properties. One concern in such a situation is that some malicious user might redistribute the model or provide a prediction service using the model without permission. One promising solution is digital watermarking, to embed a mechanism into the model so that the owner of the model can verify the ownership of the model externally. In this study, we present a novel attack method against watermark, query modification, and demonstrate that all of the existing watermark methods are vulnerable to either of query modification or existing attack method (model modification). To overcome this vulnerability, we present a novel watermarking method, exponential weighting. We experimentally show that our watermarking method achieves high verification performance of watermark even under a malicious attempt of unauthorized service providers, such as model modification and query modification, without sacrificing the predictive performance of the neural network model.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 12; 2024: 11; 2025: 7; 2026: 2.

48 papers.

Sort:

By area:

  1. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  2. 2021Proof-of-Learning: Definitions and Practicecited by 81
  3. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  4. 2023False Claims against Model Ownership Resolutioncited by 17
  5. 2023Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Processcited by 17
  6. 2024MEA-Defender: A Robust Watermark against Model Extraction Attackcited by 16
  7. 2023Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attackscited by 11
  8. 2024Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarkingcited by 11
  9. 2022Watermarking Pre-trained Encoders in Contrastive Learningcited by 10
  10. 2023Towards Robust Model Watermark via Reducing Parametric Vulnerabilitycited by 10
  11. 2022SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learningcited by 9
  12. 2023FedRight: An Effective Model Copyright Protection for Federated Learningcited by 8
36 more
  1. 2021Robust Black-box Watermarking for Deep NeuralNetwork using Inverse Document Frequencycited by 6
  2. 2021Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networkscited by 6
  3. 2023When Federated Learning meets Watermarking: A Comprehensive Overview of Techniques for Intellectual Property Protectioncited by 6
  4. 2024Box-Free Model Watermarks Are Prone to Black-Box Removal Attackscited by 6
  5. 2021Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic Imagescited by 5
  6. 2021HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networkscited by 4
  7. 2022AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learningcited by 4
  8. 2024DeepEclipse: How to Break White-Box DNN-Watermarking Schemescited by 4
  9. 2022TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Codingcited by 3
  10. 2022ROSE: A RObust and SEcure DNN Watermarkingcited by 3
  11. 2021Don't Forget to Sign the Gradients!cited by 2
  12. 2021iNNformant: Boundary Samples as Telltale Watermarkscited by 2
  13. 2022PCPT and ACPT: Copyright Protection and Traceability Scheme for DNN Modelscited by 2
  14. 2022Mixer: DNN Watermarking using Image Mixupcited by 2
  15. 2023Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Datacited by 2
  16. 2023Turn Passive to Active: A Survey on Active Intellectual Property Protection of Deep Learning Modelscited by 2
  17. 2023Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resiliencecited by 2
  18. 2024Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyondcited by 2
  19. 2024Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Datacited by 2
  20. 2024IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Methodcited by 2
  21. 2025THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Modelscited by 2
  22. 2025Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfakecited by 2
  23. 2021High-Robustness, Low-Transferability Fingerprinting of Neural Networkscited by 1
  24. 2023On Function-Coupled Watermarks for Deep Neural Networkscited by 1
  25. 2024Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layerscited by 1
  26. 2025PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibilitycited by 1
  27. 2025ChainMarks: Securing DNN Watermark with Cryptographic Chaincited by 1
  28. 2025WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networkscited by 1
  29. 2022Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision Modelscited by 0
  30. 2023From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Queryingcited by 0
  31. 2024Watermarking Recommender Systemscited by 0
  32. 2024Watermarking Decision Tree Ensemblescited by 0
  33. 2025Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attackscited by 0
  34. 2025Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distributioncited by 0
  35. 2026ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoderscited by 0
  36. 2026Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platformscited by 0