mlsanityData to 7 Oct 2026

What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network

arXiv 2307.15860 ↗First posted 29 Jul 2023cs.CV cs.CRcited by 10

Not on the map. Why?

Abstract (arXiv)

In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of illegal steal or leakage. The prior studies on remote ownership verification assume a black-box setting where the defender can query the suspicious model with specific inputs, which we identify is not enough for generation tasks. To this end, in this paper, we propose a novel IP protection scheme for GANs where ownership verification can be done by checking outputs only, without choosing the inputs (i.e., box-free setting). Specifically, we make use of the unexploited potential of the discriminator to learn a hypersphere that captures the unique distribution learned by the paired generator. Extensive evaluations on two popular GAN tasks and more than 10 GAN architectures demonstrate our proposed scheme to effectively verify the ownership. Our proposed scheme shown to be immune to popular input-based removal attacks and robust against other existing attacks. The source code and models are available at https://github.com/AbstractTeen/gan_ownership_verification

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 51 of its 74 references that are in the map. First posted on arXiv 29 Jul 2023.

Builds on

51 of 74 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  10. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  12. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
38 more
  1. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  2. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  3. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  4. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  5. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  6. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  7. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  8. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  9. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  10. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 119
  11. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 110
  12. 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistencycited by 93
  13. 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 90
  14. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 90
  15. 2019[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attackscited by 82
  16. 2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 80
  17. 2018Learning Deep Features for One-Class Classificationcited by 76
  18. 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 68
  19. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
  20. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  21. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  22. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
  23. 2022Black-box Dataset Ownership Verification via Backdoor Watermarkingcited by 57
  24. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  25. 2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
  26. 2020Model Watermarking for Image Processing Networkscited by 49
  27. 2021Deep Model Intellectual Property Protection via Deep Watermarkingcited by 47
  28. 2022Deepfake Network Architecture Attributioncited by 47
  29. 2021Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attackcited by 45
  30. 2022RepMix: Representation Mixing for Robust Attribution of Synthesized Imagescited by 39
  31. 2022Certified Neural Network Watermarks with Randomized Smoothingcited by 39
  32. 2022Rethinking the Reverse-engineering of Trojan Triggerscited by 37
  33. 2019Source Generator Attribution via Inversioncited by 21
  34. 2016Identifying and Categorizing Anomalies in Retinal Imaging Datacited by 18
  35. 2020Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Modelscited by 18
  36. 2020Simple and Effective Prevention of Mode Collapse in Deep One-Class Classificationcited by 16
  37. 2022On the Exploitation of Deepfake Model Recognitioncited by 14
  38. 2022Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networkscited by 14

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 2; 2026: 1.

10 papers.

  1. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 25
  2. 2025Model Provenance Testing for Large Language Modelscited by 15
  3. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  4. 2023Towards Robust Model Watermark via Reducing Parametric Vulnerabilitycited by 10
  5. 2024Box-Free Model Watermarks Are Prone to Black-Box Removal Attackscited by 6
  6. 2024Deepfake Media Forensics: State of the Art and Challenges Aheadcited by 6
  7. 2024Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generationcited by 3
  8. 2024Lazy Layers to Make Fine-Tuned Diffusion Models More Traceablecited by 2
  9. 2026Decoder Gradient Shields: A Family of Provable and High-Fidelity Methods Against Gradient-Based Box-Free Watermark Removalcited by 1
  10. 2025Open Set Face Forgery Detection via Dual-Level Evidence Collectioncited by 0