mlsanityData to 7 Oct 2026

CNN-generated images are surprisingly easy to spot... for now

arXiv 1912.11035 ↗First posted 23 Dec 2019cs.CVcited by 842

Not on the map. Why?

Cited by 96 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work we ask whether it is possible to create a "universal" detector for telling apart real images from these generated by a CNN, regardless of architecture or dataset used. To test this, we collect a dataset consisting of fake images generated by 11 different CNN-based image generator models, chosen to span the space of commonly used architectures today (ProGAN, StyleGAN, BigGAN, CycleGAN, StarGAN, GauGAN, DeepFakes, cascaded refinement networks, implicit maximum likelihood estimation, second-order attention super-resolution, seeing-in-the-dark). We demonstrate that, with careful pre- and post-processing and data augmentation, a standard image classifier trained on only one specific CNN generator (ProGAN) is able to generalize surprisingly well to unseen architectures, datasets, and training methods (including the just released StyleGAN2). Our findings suggest the intriguing possibility that today's CNN-generated images share some common systematic flaws, preventing them from achieving realistic image synthesis. Code and pre-trained networks are available at https://peterwang512.github.io/CNNDetection/ .

Key facts. Cited by 842 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 79; 2022: 90; 2023: 104; 2024: 155; 2025: 199; 2026: 215.

842 papers.

Sort:

By area:

  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  2. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  3. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  4. 2023Zero-shot Image-to-Image Translationcited by 503
  5. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  6. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  7. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  8. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  9. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  10. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  11. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  12. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 241
38 more
  1. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  2. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  3. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  4. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  5. 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Modelscited by 167
  6. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  7. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  8. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  9. 2022EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Modelcited by 151
  10. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  11. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  12. 2021Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detectioncited by 133
  13. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  14. 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
  15. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  16. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 124
  17. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  18. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  19. 2023PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detectioncited by 119
  20. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  21. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  22. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  23. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 111
  24. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  25. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  26. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  27. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  28. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  29. 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
  30. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  31. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  32. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88
  33. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 88
  34. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  35. 2024DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmarkcited by 85
  36. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  37. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  38. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82

50 most cited of 842 All 842 (JSON)