mlsanityData to 13 Oct 2026

What makes fake images detectable? Understanding properties that generalize

arXiv 2008.10588 ↗First posted 24 Aug 2020cs.CVcited by 273

Not on the map. Why?

Cited by 36 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The quality of image generation and manipulation is reaching impressive levels, making it increasingly difficult for a human to distinguish between what is real and what is fake. However, deep networks can still pick up on the subtle artifacts in these doctored images. We seek to understand what properties of fake images make them detectable and identify what generalizes across different model architectures, datasets, and variations in training. We use a patch-based classifier with limited receptive fields to visualize which regions of fake images are more easily detectable. We further show a technique to exaggerate these detectable properties and demonstrate that, even when the image generator is adversarially finetuned against a fake image classifier, it is still imperfect and leaves detectable artifacts in certain image patches. Code is available at https://chail.github.io/patch-forensics/.

Key facts. Cited by 273 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 23; 2022: 34; 2023: 43; 2024: 61; 2025: 68; 2026: 44.

273 papers.

Sort:

By area:

  1. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,104
  2. 2023Zero-shot Image-to-Image Translationcited by 503
  3. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 488
  4. 2023DIRE for Diffusion-Generated Image Detectioncited by 389
  5. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 303
  6. 2022On the detection of synthetic images generated by diffusion modelscited by 283
  7. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 242
  8. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 181
  9. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
  10. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 159
  11. 2022EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Modelcited by 151
  12. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
38 more
  1. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  2. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  3. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  4. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 112
  5. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  6. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  7. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 103
  8. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  9. 2022Protecting Celebrities from DeepFake with Identity Consistency Transformercited by 95
  10. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 89
  11. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  12. 2021Face Forensics in the Wildcited by 87
  13. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 85
  14. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  15. 2024EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesiscited by 79
  16. 2023AltFreezing for More General Video Face Forgery Detectioncited by 78
  17. 2021Multimodal Conditional Image Synthesis with Product-of-Experts GANscited by 75
  18. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 73
  19. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  20. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  21. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 67
  22. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 66
  23. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
  24. 2023Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for nowcited by 61
  25. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  26. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 59
  27. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  28. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  29. 2023Online Detection of AI-Generated Imagescited by 55
  30. 2021Ensembling with Deep Generative Viewscited by 53
  31. 2021On Aliased Resizing and Surprising Subtleties in GAN Evaluationcited by 51
  32. 2024Real-Time Deepfake Detection in the Real-Worldcited by 50
  33. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  34. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  35. 2022Deepfake Network Architecture Attributioncited by 47
  36. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  37. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  38. 2024D3: Scaling Up Deepfake Detection by Learning from Discrepancycited by 44

50 most cited of 273 All 273 (JSON)