mlsanityData to 7 Oct 2026

Alteration-free and Model-agnostic Origin Attribution of Generated Images

arXiv 2305.18439 ↗First posted 29 May 2023cs.CV cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Recently, there has been a growing attention in image generation models. However, concerns have emerged regarding potential misuse and intellectual property (IP) infringement associated with these models. Therefore, it is necessary to analyze the origin of images by inferring if a specific image was generated by a particular model, i.e., origin attribution. Existing methods are limited in their applicability to specific types of generative models and require additional steps during training or generation. This restricts their use with pre-trained models that lack these specific operations and may compromise the quality of image generation. To overcome this problem, we first develop an alteration-free and model-agnostic origin attribution method via input reverse-engineering on image generation models, i.e., inverting the input of a particular model for a specific image. Given a particular model, we first analyze the differences in the hardness of reverse-engineering tasks for the generated images of the given model and other images. Based on our analysis, we propose a method that utilizes the reconstruction loss of reverse-engineering to infer the origin. Our proposed method effectively distinguishes between generated images from a specific generative model and other images, including those generated by different models and real images.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 46 of its 68 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

46 of 68 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017Neural Discrete Representation Learningcited by 4,650
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  11. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  12. 2023Consistency Modelscited by 1,778
34 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2017Mixed Precision Trainingcited by 1,135
  5. 2023Extracting Training Data from Diffusion Modelscited by 723
  6. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  7. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  8. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  9. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  10. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  11. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  12. 2021Multi-attentional Deepfake Detectioncited by 339
  13. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
  14. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  15. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  16. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  17. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  18. 2018Do GANs leave artificial fingerprints?cited by 188
  19. 2019Controllable Text-to-Image Generationcited by 187
  20. 2020Automatic Detection of Machine Generated Text: A Critical Surveycited by 160
  21. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  22. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 90
  23. 2023MGTBench: Benchmarking Machine-Generated Text Detectioncited by 90
  24. 2022BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learningcited by 82
  25. 2019Unmasking DeepFakes with simple Featurescited by 78
  26. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  27. 2021Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attackcited by 45
  28. 2023UNICORN: A Unified Backdoor Trigger Inversion Frameworkcited by 44
  29. 2022Training with More Confidence: Mitigating Injected and Natural Backdoors During Trainingcited by 38
  30. 2023A Pathway Towards Responsible AI Generated Contentcited by 38
  31. 2022Rethinking the Reverse-engineering of Trojan Triggerscited by 37
  32. 2023NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Modelscited by 33
  33. 2021Unsupervised and Distributional Detection of Machine-Generated Textcited by 23
  34. 2022Backdoor Vulnerabilities in Normally Trained Deep Learning Modelscited by 12

Built on by

Cited by year

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

4 papers.

  1. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 83
  2. 2024Which Model Generated This Image? A Model-Agnostic Approach for Origin Attributioncited by 15
  3. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  4. 2025StyleSentinel: Reliable Artistic Copyright Verification via Stylistic Fingerprintscited by 1