mlsanityData to 7 Oct 2026

Single-Model Attribution of Generative Models Through Final-Layer Inversion

arXiv 2306.06210 ↗First posted 26 May 2023cs.CV cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 49 of its 84 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

49 of 84 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
37 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  3. 2016Least Squares Generative Adversarial Networkscited by 1,000
  4. 2019Modeling Tabular data using Conditional GANcited by 695
  5. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  6. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  7. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  8. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  9. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  10. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
  11. 2020Media Forensics and DeepFakes: an overviewcited by 208
  12. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  13. 2018Do GANs leave artificial fingerprints?cited by 188
  14. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  15. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 138
  16. 2016Energy-based Generative Adversarial Networkcited by 119
  17. 2019Deep Learning for Deepfakes Creation and Detection: A Surveycited by 102
  18. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 90
  19. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  20. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  21. 2021On the Frequency Bias of Generative Modelscited by 60
  22. 2019Incremental learning for the detection and classification of GAN-generated imagescited by 58
  23. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  24. 2021Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attackcited by 45
  25. 2019Inverting Deep Generative models, One layer at a timecited by 33
  26. 2019Bridging the Gap Between f-GANs and Wasserstein GANscited by 23
  27. 2021More Real than Real: A Study on Human Visual Perception of Synthetic Facescited by 23
  28. 2019Source Generator Attribution via Inversioncited by 21
  29. 2023Attributing Image Generative Models using Latent Fingerprintscited by 20
  30. 2022Efficient Image Generation with Variadic Attention Headscited by 17
  31. 2020Decentralized Attribution of Generative Modelscited by 16
  32. 2022medigan: a Python library of pretrained generative models for medical image synthesiscited by 14
  33. 2022Statistical guarantees for sparse deep learningcited by 9
  34. 2022Sharing Generative Models Instead of Private Data: A Simulation Study on Mammography Patch Classificationcited by 7
  35. 2019DCGANs for Realistic Breast Mass Augmentation in X-ray Mammographycited by 6
  36. 2019Scalable Fine-grained Generated Image Classification Based on Deep Metric Learningcited by 6
  37. 2018Compressed Sensing Using Binary Matrices of Nearly Optimal Dimensionscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 3.

10 papers.

  1. 2024Are CLIP features all you need for Universal Synthetic Image Origin Attribution?cited by 14
  2. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  3. 2024Detecting Origin Attribution for Text-to-Image Diffusion Modelscited by 7
  4. 2025Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Contentcited by 1
  5. 2025Untraceable DeepFakes via Traceable Fingerprint Eliminationcited by 1
  6. 2025PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Imagescited by 1
  7. 2026Exploiting the Final Component of Generator Architectures for AI-Generated Image Detectioncited by 1
  8. 2024Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attributioncited by 0
  9. 2026Scalable Black-Box Model Attribution for Imagescited by 0
  10. 2026FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generatorscited by 0