mlsanityData to 7 Oct 2026

Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack

arXiv 2102.04362 ↗First posted 8 Feb 2021cs.CR cs.AI cs.CVcited by 45

Not on the map. Why?

Cited by 20 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Ever since Machine Learning as a Service (MLaaS) emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties. To the best of our knowledge, one of the prominent deep learning models - Generative Adversarial Networks (GANs) which has been widely used to create photorealistic image are totally unprotected despite the existence of pioneering IPR protection methodology for Convolutional Neural Networks (CNNs). This paper therefore presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs. Empirically, we show that the proposed method does not compromise the original GANs performance (i.e. image generation, image super-resolution, style transfer), and at the same time, it is able to withstand both removal and ambiguity attacks against embedded watermarks.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 14 of its 34 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

14 of 34 references.

References · 14

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  6. 2017Generative Adversarial Networks: An Overviewcited by 588
  7. 2018HiDDeN: Hiding Data With Deep Networkscited by 384
  8. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  9. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  10. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
  11. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
  12. 2020Passport-aware Normalization for Deep Model Protectioncited by 42
2 more
  1. 2018DeepMarks: A Digital Fingerprinting Framework for Deep Neural Networkscited by 23
  2. 2018DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Modelscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 20; 2024: 10; 2025: 4; 2026: 1.

45 papers.

Sort:

By area:

  1. 2023A Recipe for Watermarking Diffusion Modelscited by 136
  2. 2023Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoningcited by 91
  3. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
  4. 2023WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Modelscited by 51
  5. 2023Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Modelscited by 42
  6. 2022Supervised GAN Watermarking for Intellectual Property Protectioncited by 39
  7. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  8. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  9. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 34
  10. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Modelscited by 26
  11. 2022FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Modelcited by 25
  12. 2023Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscationcited by 20
33 more
  1. 2024Watermarking Techniques for Large Language Models: A Surveycited by 20
  2. 2023Intellectual Property Protection of Diffusion Models via the Watermark Diffusion Processcited by 17
  3. 2024GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesiscited by 17
  4. 2023Copyright Protection and Accountability of Generative AI:Attack, Watermarking and Attributioncited by 15
  5. 2022On the Exploitation of Deepfake Model Recognitioncited by 14
  6. 2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
  7. 2023Functional Invariants to Watermark Large Transformerscited by 14
  8. 2024Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarkingcited by 11
  9. 2023Single-Model Attribution of Generative Models Through Final-Layer Inversioncited by 10
  10. 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
  11. 2023Wide Flat Minimum Watermarking for Robust Ownership Verification of GANscited by 10
  12. 2023Invisible Watermarking for Audio Generation Diffusion Modelscited by 7
  13. 2023Robust Retraining-free GAN Fingerprinting via Personalized Normalizationcited by 6
  14. 2022Cracking White-box DNN Watermarks via Invariant Neuron Transformscited by 5
  15. 2024Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retrainingcited by 5
  16. 2025AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstructioncited by 5
  17. 2022Robust and Large-Payload DNN Watermarking via Fixed, Distribution-Optimized, Weightscited by 4
  18. 2023Alteration-free and Model-agnostic Origin Attribution of Generated Imagescited by 4
  19. 2023T2IW: Joint Text to Image & Watermark Generationcited by 4
  20. 2025Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarkingcited by 4
  21. 2024Lazy Layers to Make Fine-Tuned Diffusion Models More Traceablecited by 2
  22. 2024Proactive Schemes: A Survey of Adversarial Attacks for Social Goodcited by 2
  23. 2024IDEA: An Inverse Domain Expert Adaptation Based Active DNN IP Protection Methodcited by 2
  24. 2021Fingerprinting Image-to-Image Generative Adversarial Networkscited by 1
  25. 2022Knowledge-Free Black-Box Watermark and Ownership Proof for Image Classification Neural Networkscited by 1
  26. 2022DeepHider: A Covert NLP Watermarking Framework Based on Multi-task Learningcited by 1
  27. 2022An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networkscited by 1
  28. 2023Ownership Protection of Generative Adversarial Networkscited by 1
  29. 2026Attesting Model Lineage by Consisted Knowledge Evolution with Fine-Tuning Trajectorycited by 1
  30. 2023OVLA: Neural Network Ownership Verification using Latent Watermarkscited by 0
  31. 2024Embedding Watermarks in Diffusion Process for Model Intellectual Property Protectioncited by 0
  32. 2025Learning Generalizable and Efficient Image Watermarking via Hierarchical Two-Stage Optimizationcited by 0
  33. 2025SMS: Self-supervised Model Seeding for Verification of Machine Unlearningcited by 0