mlsanityData to 7 Oct 2026

Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution

arXiv 2404.02697 ↗First posted 3 Apr 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Recent progress in visual generative models enables the generation of high-quality images. To prevent the misuse of generated images, it is important to identify the origin model that generates them. In this work, we study the origin attribution of generated images in a practical setting where only a few images generated by a source model are available and the source model cannot be accessed. The goal is to check if a given image is generated by the source model. We first formulate this problem as a few-shot one-class classification task. To solve the task, we propose OCC-CLIP, a CLIP-based framework for few-shot one-class classification, enabling the identification of an image's source model, even among multiple candidates. Extensive experiments corresponding to various generative models verify the effectiveness of our OCC-CLIP framework. Furthermore, an experiment based on the recently released DALL-E 3 API verifies the real-world applicability of our solution.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 50 of its 71 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

50 of 71 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2020Denoising Diffusion Implicit Modelscited by 9,655
  10. 2016Densely Connected Convolutional Networkscited by 6,691
  11. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  12. 2022Generative Adversarial Networkscited by 5,603
38 more
  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  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. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  11. 2019An Introduction to Variational Autoencoderscited by 997
  12. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  13. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  14. 2021Going deeper with Image Transformerscited by 759
  15. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  16. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  17. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  18. 2023MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Modelscited by 255
  19. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  20. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  21. 2020Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Datacited by 200
  22. 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Modelscited by 167
  23. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 90
  24. 2023GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesiscited by 84
  25. 2023Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generationcited by 69
  26. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  27. 2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
  28. 2021Are Vision Transformers Robust to Patch Perturbations?cited by 39
  29. 2023Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Modelscited by 30
  30. 2022Towards Efficient Adversarial Training on Vision Transformerscited by 29
  31. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  32. 2024Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Modelcited by 22
  33. 2019Improving the Robustness of Capsule Networks to Image Affine Transformationscited by 21
  34. 2022Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removalcited by 18
  35. 2020Few-Shot One-Class Classification via Meta-Learningcited by 17
  36. 2020Decentralized Attribution of Generative Modelscited by 16
  37. 2023Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averagingcited by 14
  38. 2023Alteration-free and Model-agnostic Origin Attribution of Generated Imagescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 4.

15 papers.

Sort:

By area:

  1. 2025Rethinking Data Protection in the (Generative) Artificial Intelligence Eracited by 17
  2. 2025Few-Shot Learner Generalizes Across AI-Generated Image Detectioncited by 13
  3. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  4. 2024Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Modelscited by 7
  5. 2025Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samplescited by 6
  6. 2025Team NYCU at Defactify4: Robust Detection and Source Identification of AI-Generated Images Using CNN and CLIP-Based Modelscited by 2
  7. 2024The Visual Counter Turing Test (VCT2): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (VAI)cited by 1
  8. 2025Position: It's Time to Act on the Risk of Efficient Personalized Text Generationcited by 1
  9. 2025Few-Shot Class-Incremental Model Attribution Using Learnable Representation From CLIP-ViT Featurescited by 1
  10. 2024Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attributioncited by 0
  11. 2025Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagerycited by 0
  12. 2026DNA: Dual-stage Native Attribution for Generated Image Source Tracingcited by 0
3 more
  1. 2026IP Protection in the Era of Visual Generative AI: A Surveycited by 0
  2. 2026Scalable Black-Box Model Attribution for Imagescited by 0
  3. 2026FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generatorscited by 0