mlsanityData to 7 Oct 2026

Towards the Detection of Diffusion Model Deepfakes

arXiv 2210.14571 ↗First posted 26 Oct 2022cs.CVcited by 111

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

In the course of the past few years, diffusion models (DMs) have reached an unprecedented level of visual quality. However, relatively little attention has been paid to the detection of DM-generated images, which is critical to prevent adverse impacts on our society. In contrast, generative adversarial networks (GANs), have been extensively studied from a forensic perspective. In this work, we therefore take the natural next step to evaluate whether previous methods can be used to detect images generated by DMs. Our experiments yield two key findings: (1) state-of-the-art GAN detectors are unable to reliably distinguish real from DM-generated images, but (2) re-training them on DM-generated images allows for almost perfect detection, which remarkably even generalizes to GANs. Together with a feature space analysis, our results lead to the hypothesis that DMs produce fewer detectable artifacts and are thus more difficult to detect compared to GANs. One possible reason for this is the absence of grid-like frequency artifacts in DM-generated images, which are a known weakness of GANs. However, we make the interesting observation that diffusion models tend to underestimate high frequencies, which we attribute to the learning objective.

Key facts. Cited by 111 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 57 of its 99 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

57 of 99 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  7. 2020Denoising Diffusion Implicit Modelscited by 9,655
  8. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  9. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  10. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
38 more
  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2021Variational Diffusion Modelscited by 1,145
  9. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  10. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  11. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  12. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  13. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  14. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  15. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  16. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  17. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
  18. 2020What makes fake images detectable? Understanding properties that generalizecited by 272
  19. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  20. 2020Media Forensics and DeepFakes: an overviewcited by 208
  21. 2021Projected GANs Converge Fastercited by 204
  22. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  23. 2018Do GANs leave artificial fingerprints?cited by 188
  24. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  25. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  26. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 138
  27. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  28. 2018ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detectioncited by 104
  29. 2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
  30. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  31. 2021On the Frequency Bias of Generative Modelscited by 60
  32. 2020Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlightscited by 59
  33. 2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
  34. 2020SSD-GAN: Measuring the Realness in the Spatial and Spectral Domainscited by 38
  35. 2019On the generalization of GAN image forensicscited by 36
  36. 2020Spatial Frequency Bias in Convolutional Generative Adversarial Networkscited by 35
  37. 2022Lighting (In)consistency of Paint by Textcited by 35
  38. 2022Perspective (In)consistency of Paint by Textcited by 34

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 25; 2024: 47; 2025: 28; 2026: 11.

111 papers.

Sort:

By area:

  1. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  2. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  3. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  4. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  5. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  6. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  7. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
  8. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  9. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 88
  10. 2024SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safetycited by 75
  11. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  12. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
38 more
  1. 2024Common Sense Reasoning for Deepfake Detectioncited by 64
  2. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 58
  3. 2023Multimodal Automated Fact-Checking: A Surveycited by 51
  4. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  5. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  6. 2023Exposing the Fake: Effective Diffusion-Generated Images Detectioncited by 48
  7. 2024LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detectioncited by 47
  8. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  9. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 43
  10. 2024Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasetscited by 43
  11. 2024Diffusion Facial Forgery Detectioncited by 41
  12. 2024Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Imagescited by 41
  13. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  14. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  15. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  16. 2024DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysiscited by 29
  17. 2023DeepFake-Adapter: Dual-Level Adapter for DeepFake Detectioncited by 26
  18. 2023Weakly-supervised deepfake localization in diffusion-generated imagescited by 24
  19. 2023A Representative Study on Human Detection of Artificially Generated Media Across Countriescited by 22
  20. 2024Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?cited by 21
  21. 2024Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detectioncited by 21
  22. 2024Bi-LORA: A Vision-Language Approach for Synthetic Image Detectioncited by 20
  23. 2024Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videoscited by 20
  24. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Spacecited by 19
  25. 2024DeCLIP: Decoding CLIP representations for deepfake localizationcited by 17
  26. 2023Variational Bayesian Imaging with an Efficient Surrogate Score-based Priorcited by 16
  27. 2024An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscapecited by 16
  28. 2024Language-guided Hierarchical Fine-grained Image Forgery Detection and Localizationcited by 16
  29. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  30. 2024Characteristics and prevalence of fake social media profiles with AI-generated facescited by 14
  31. 2024SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Frameworkcited by 14
  32. 2024Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yetcited by 13
  33. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Imagescited by 13
  34. 2024StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Modelcited by 12
  35. 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detectioncited by 10
  36. 2025LOTA: Bit-Planes Guided AI-Generated Image Detectioncited by 10
  37. 2024Masked Conditional Diffusion Model for Enhancing Deepfake Detectioncited by 9
  38. 2025Training-free Detection of AI-generated images via Cropping Robustnesscited by 9

50 most cited of 111 All 111 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022On the detection of synthetic images generated by diffusion models
  2. 2025Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection
  3. 2025Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review
  4. 2024DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection
  5. 2022Progressive Distillation for Fast Sampling of Diffusion Models
  6. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  7. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey
  8. 2023Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Models