mlsanityData to 14 Oct 2026

Local Statistics for Generative Image Detection

arXiv 2310.16684 ↗First posted 25 Oct 2023cs.CVcited by 5

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

Abstract (arXiv)

Diffusion models (DMs) are generative models that learn to synthesize images from Gaussian noise. DMs can be trained to do a variety of tasks such as image generation and image super-resolution. Researchers have made significant improvements in the capability of synthesizing photorealistic images in the past few years. These successes also hasten the need to address the potential misuse of synthesized images. In this paper, we highlighted the effectiveness of Bayer pattern and local statistics in distinguishing digital camera images from DM-generated images. We further hypothesized that local statistics should be used to address the spatial non-stationarity problems in images. We showed that our approach produced promising results for distinguishing real images from synthesized images. This approach is also robust to various perturbations such as image resizing and JPEG compression.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 36 of its 47 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

36 of 47 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023DIRE for Diffusion-Generated Image Detection16 Mar
  2. 2022On the detection of synthetic images generated by diffusion models1 Nov
  3. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models26 Oct
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  9. 2022Generative Adversarial Networkscited by 5,627
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
19 more
  1. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  2. 2021Variational Diffusion Modelscited by 1,153
  3. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  5. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  6. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  7. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  8. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 319
  9. 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 297
  10. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  11. 2022Diffusion Models for Medical Anomaly Detectioncited by 232
  12. 2020Media Forensics and DeepFakes: an overviewcited by 209
  13. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Modelscited by 192
  14. 2018Do GANs leave artificial fingerprints?cited by 190
  15. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  16. 2018Noiseprint: a CNN-based camera model fingerprintcited by 114
  17. 2022Lighting (In)consistency of Paint by Textcited by 35
  18. 2023ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detectioncited by 35
  19. 2022Perspective (In)consistency of Paint by Textcited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 2.

5 papers.

  1. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76
  2. 2024The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methodscited by 4
  3. 2025Rethinking Individual Fairness in Deepfake Detectioncited by 4
  4. 2026Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cuescited by 1
  5. 2026Towards Generalizable Deepfake Detection via Real Distribution Bias Correctioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion Noise Feature: Accurate and Fast Generated Image Detection
  2. 2024Diffusion Models, Image Super-Resolution And Everything: A Survey
  3. 2024Diffusion Models in Low-Level Vision: A Survey
  4. 2024Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image Detection
  5. 2026FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection
  6. 2024Diffusion Model-Based Image Editing: A Survey
  7. 2024Detecting AutoEncoder is Enough to Catch LDM Generated Images
  8. 2024Aligned Datasets Improve Detection of Latent Diffusion-Generated Images