mlsanityData to 7 Oct 2026

Fourier Spectrum Discrepancies in Deep Network Generated Images

arXiv 1911.06465 ↗First posted 15 Nov 2019eess.IV cs.LG stat.MLcited by 138

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Advancements in deep generative models such as generative adversarial networks and variational autoencoders have resulted in the ability to generate realistic images that are visually indistinguishable from real images, which raises concerns about their potential malicious usage. In this paper, we present an analysis of the high-frequency Fourier modes of real and deep network generated images and show that deep network generated images share an observable, systematic shortcoming in replicating the attributes of these high-frequency modes. Using this, we propose a detection method based on the frequency spectrum of the images which is able to achieve an accuracy of up to 99.2% in classifying real and deep network generated images from various GAN and VAE architectures on a dataset of 5000 images with as few as 8 training examples. Furthermore, we show the impact of image transformations such as compression, cropping, and resolution reduction on the classification accuracy and suggest a method for modifying the high-frequency attributes of deep network generated images to mimic real images.

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 18; 2023: 27; 2024: 19; 2025: 33; 2026: 28.

138 papers.

Sort:

By area:

  1. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  2. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  3. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
  4. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
  5. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  6. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  7. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  8. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  9. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  10. 2021On the Frequency Bias of Generative Modelscited by 60
  11. 2022Will Large-scale Generative Models Corrupt Future Datasets?cited by 59
  12. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
38 more
  1. 2023Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detectioncited by 50
  2. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  3. 2021ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Imagescited by 48
  4. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  5. 2025A Fourier Space Perspective on Diffusion Modelscited by 48
  6. 2021Spectral Unsupervised Domain Adaptation for Visual Recognitioncited by 40
  7. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36
  8. 2022Detecting and Recovering Sequential DeepFake Manipulationcited by 34
  9. 2022Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?cited by 32
  10. 2023Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learningcited by 32
  11. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  12. 2023DeepFake-Adapter: Dual-Level Adapter for DeepFake Detectioncited by 26
  13. 2021Wavelet-Packets for Deepfake Image Analysis and Detectioncited by 25
  14. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  15. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  16. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  17. 2024Mixture of Low-rank Experts for Transferable AI-Generated Image Detectioncited by 21
  18. 2023Detecting Generated Images by Real Images Onlycited by 20
  19. 2024ManiFPT: Defining and Analyzing Fingerprints of Generative Modelscited by 18
  20. 2021SWAGAN: A Style-based Wavelet-driven Generative Modelcited by 17
  21. 2022Making DeepFakes more spurious: evading deep face forgery detection via trace removal attackcited by 16
  22. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  23. 2022FedForgery: Generalized Face Forgery Detection with Residual Federated Learningcited by 12
  24. 2024Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attackscited by 12
  25. 2024StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Modelcited by 12
  26. 2025Methods and Trends in Detecting AI-Generated Images: A Comprehensive Reviewcited by 12
  27. 2021Exploring The Effect of High-frequency Components in GANs Trainingcited by 10
  28. 2023Single-Model Attribution of Generative Models Through Final-Layer Inversioncited by 10
  29. 2023DRAW: Defending Camera-shooted RAW against Image Manipulationcited by 10
  30. 2023GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusionscited by 10
  31. 2025LOTA: Bit-Planes Guided AI-Generated Image Detectioncited by 10
  32. 2021Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Imagescited by 9
  33. 2022Hierarchical Forgery Classifier On Multi-modality Face Forgery Cluescited by 9
  34. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  35. 2024On the Exploitation of DCT-Traces in the Generative-AI Domaincited by 9
  36. 2021USIS: Unsupervised Semantic Image Synthesiscited by 8
  37. 2022Investigating and Explaining the Frequency Bias in Image Classificationcited by 8
  38. 2023On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvementcited by 8

50 most cited of 138 All 138 (JSON)