mlsanityData to 7 Oct 2026

Leveraging Frequency Analysis for Deep Fake Image Recognition

arXiv 2003.08685 ↗First posted 19 Mar 2020cs.CV eess.IVcited by 501

Not on the map. Why?

Cited by 65 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While deep fake images have been thoroughly investigated in the image domain - a classical approach from the area of image forensics - an analysis in the frequency domain has been missing so far. In this paper, we address this shortcoming and our results reveal that in frequency space, GAN-generated images exhibit severe artifacts that can be easily identified. We perform a comprehensive analysis, showing that these artifacts are consistent across different neural network architectures, data sets, and resolutions. In a further investigation, we demonstrate that these artifacts are caused by upsampling operations found in all current GAN architectures, indicating a structural and fundamental problem in the way images are generated via GANs. Based on this analysis, we demonstrate how the frequency representation can be used to identify deep fake images in an automated way, surpassing state-of-the-art methods.

Key facts. Cited by 501 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 41; 2023: 69; 2024: 93; 2025: 129; 2026: 131.

501 papers.

Sort:

By area:

  1. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  2. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  3. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  4. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  5. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  6. 2023FreeU: Free Lunch in Diffusion U-Netcited by 195
  7. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  8. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  9. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 177
  10. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  11. 2021Exploring Temporal Coherence for More General Video Face Forgery Detectioncited by 158
  12. 2021Rethinking the Backdoor Attacks' Triggers: A Frequency Perspectivecited by 155
38 more
  1. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  2. 2022Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detectioncited by 130
  3. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 124
  4. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  5. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  6. 2022Diffusion Probabilistic Model Made Slimcited by 121
  7. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
  8. 2023PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detectioncited by 119
  9. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  10. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 111
  11. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  12. 2021Dual Contrastive Learning for General Face Forgery Detectioncited by 100
  13. 2023TALL: Thumbnail Layout for Deepfake Video Detectioncited by 100
  14. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  15. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88
  16. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 88
  17. 2021Face Forensics in the Wildcited by 87
  18. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 84
  19. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  20. 2024TC4D: Trajectory-Conditioned Text-to-4D Generationcited by 76
  21. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  22. 2023Evading Watermark based Detection of AI-Generated Contentcited by 74
  23. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  24. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  25. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 68
  26. 2024Deepfake Generation and Detection: A Benchmark and Surveycited by 66
  27. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 65
  28. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  29. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  30. 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detectioncited by 60
  31. 2021On the Frequency Bias of Generative Modelscited by 60
  32. 2021Exploiting Fine-grained Face Forgery Clues via Progressive Enhancement Learningcited by 60
  33. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  34. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
  35. 2023Online Detection of AI-Generated Imagescited by 55
  36. 2021Ensembling with Deep Generative Viewscited by 53
  37. 2023TrustMark: Universal Watermarking for Arbitrary Resolution Imagescited by 50
  38. 2024Zero-Shot Detection of AI-Generated Imagescited by 50

50 most cited of 501 All 501 (JSON)