mlsanityData to 7 Oct 2026

Towards Discovery and Attribution of Open-world GAN Generated Images

arXiv 2105.04580 ↗First posted 10 May 2021cs.CV cs.LGcited by 66

Not on the map. Why?

Abstract (arXiv)

With the recent progress in Generative Adversarial Networks (GANs), it is imperative for media and visual forensics to develop detectors which can identify and attribute images to the model generating them. Existing works have shown to attribute images to their corresponding GAN sources with high accuracy. However, these works are limited to a closed set scenario, failing to generalize to GANs unseen during train time and are therefore, not scalable with a steady influx of new GANs. We present an iterative algorithm for discovering images generated from previously unseen GANs by exploiting the fact that all GANs leave distinct fingerprints on their generated images. Our algorithm consists of multiple components including network training, out-of-distribution detection, clustering, merge and refine steps. Through extensive experiments, we show that our algorithm discovers unseen GANs with high accuracy and also generalizes to GANs trained on unseen real datasets. We additionally apply our algorithm to attribution and discovery of GANs in an online fashion as well as to the more standard task of real/fake detection. Our experiments demonstrate the effectiveness of our approach to discover new GANs and can be used in an open-world setup.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

46 of 64 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2016Learning without Forgettingcited by 2,465
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
34 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  4. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  5. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  6. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  7. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  8. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  9. 2017Fake News Detection on Social Media: A Data Mining Perspectivecited by 334
  10. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  11. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
  12. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  13. 2014Towards Open World Recognitioncited by 226
  14. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  15. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  16. 2018Do GANs leave artificial fingerprints?cited by 188
  17. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  18. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  19. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  20. 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
  21. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 118
  22. 2017The Cramer Distance as a Solution to Biased Wasserstein Gradientscited by 116
  23. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
  24. 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
  25. 2019ClusterFit: Improving Generalization of Visual Representationscited by 82
  26. 2015The Extreme Value Machinecited by 78
  27. 2019Deep Spectral Clustering using Dual Autoencoder Networkcited by 71
  28. 2018Fashion-Gen: The Generative Fashion Dataset and Challengecited by 65
  29. 2019Incremental learning for the detection and classification of GAN-generated imagescited by 58
  30. 2019High-Fidelity Image Generation With Fewer Labelscited by 51
  31. 2019Learning to Cluster Faces on an Affinity Graphcited by 50
  32. 2018Open-world Learning and Application to Product Classificationcited by 39
  33. 2019Source Generator Attribution via Inversioncited by 21
  34. 2020Open-World Class Discovery with Kernel Networkscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 18; 2024: 15; 2025: 13; 2026: 10.

66 papers.

Sort:

By area:

  1. 2022Generalized Category Discoverycited by 209
  2. 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Modelscited by 167
  3. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  4. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  5. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  6. 2022RepMix: Representation Mixing for Robust Attribution of Synthesized Imagescited by 39
  7. 2023PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generatorscited by 34
  8. 2023Progressive Open Space Expansion for Open-Set Model Attributioncited by 32
  9. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  10. 2023Contrastive Pseudo Learning for Open-World DeepFake Attributioncited by 27
  11. 2022Difficulty-Aware Simulator for Open Set Recognitioncited by 24
  12. 2022Model Attribution of Face-swap Deepfake Videoscited by 17
38 more
  1. 2022Open-Set Semi-Supervised Object Detectioncited by 17
  2. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  3. 2024Which Model Generated This Image? A Model-Agnostic Approach for Origin Attributioncited by 15
  4. 2024Are CLIP features all you need for Universal Synthetic Image Origin Attribution?cited by 14
  5. 2024Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yetcited by 13
  6. 2025Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Modelscited by 13
  7. 2023Open Set Synthetic Image Source Attributioncited by 12
  8. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 12
  9. 2025Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Imagescited by 11
  10. 2023Single-Model Attribution of Generative Models Through Final-Layer Inversioncited by 10
  11. 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networkcited by 10
  12. 2023GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusionscited by 10
  13. 2022An Overview of Recent Work in Media Forensics: Methods and Threatscited by 7
  14. 2024Detecting Origin Attribution for Text-to-Image Diffusion Modelscited by 7
  15. 2023Open Set Classification of GAN-based Image Manipulations via a ViT-based Hybrid Architecturecited by 6
  16. 2024BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attributioncited by 6
  17. 2023Model Synthesis for Zero-Shot Model Attributioncited by 5
  18. 2024Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?cited by 5
  19. 2024Are handcrafted filters helpful for attributing AI-generated images?cited by 5
  20. 2025DATA: Multi-Disentanglement based Contrastive Learning for Open-World Semi-Supervised Deepfake Attributioncited by 5
  21. 2025Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learningcited by 5
  22. 2023Detecting Adversarial Faces Using Only Real Face Self-Perturbationscited by 4
  23. 2024Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discoverycited by 4
  24. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  25. 2025SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstructioncited by 4
  26. 2023CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videoscited by 3
  27. 2024Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Modelscited by 3
  28. 2024Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generationcited by 3
  29. 2026Attribution as Retrieval: Model-Agnostic AI-Generated Image Attributioncited by 3
  30. 2026IncreFA: Breaking the Static Wall of Generative Model Attributioncited by 3
  31. 2022Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detectioncited by 2
  32. 2024Lazy Layers to Make Fine-Tuned Diffusion Models More Traceablecited by 2
  33. 2025FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakescited by 2
  34. 2025SAGA: Source Attribution of Generative AI Videoscited by 2
  35. 2025Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprintscited by 2
  36. 2023FAKEPCD: Fake Point Cloud Detection via Source Attributioncited by 1
  37. 2025PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attributioncited by 1
  38. 2025Untraceable DeepFakes via Traceable Fingerprint Eliminationcited by 1

50 most cited of 66 All 66 (JSON)