mlsanityData to 14 Oct 2026

Detecting GAN generated Fake Images using Co-occurrence Matrices

arXiv 1903.06836 ↗First posted 15 Mar 2019cs.CV eess.IVcited by 124

Not on the map. Why?

Abstract (arXiv)

The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as Image-to-Image translations, DeepFakes, and other automated methods have become increasingly popular in creating fake images. In this paper, we propose a novel approach to detect GAN generated fake images using a combination of co-occurrence matrices and deep learning. We extract co-occurrence matrices on three color channels in the pixel domain and train a model using a deep convolutional neural network (CNN) framework. Experimental results on two diverse and challenging GAN datasets comprising more than 56,000 images based on unpaired image-to-image translations (cycleGAN [1]) and facial attributes/expressions (StarGAN [2]) show that our approach is promising and achieves more than 99% classification accuracy in both datasets. Further, our approach also generalizes well and achieves good results when trained on one dataset and tested on the other.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 12; 2023: 23; 2024: 23; 2025: 31; 2026: 15.

124 papers.

Sort:

By area:

  1. 2023Zero-shot Image-to-Image Translationcited by 505
  2. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  3. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  4. 2024A Sanity Check for AI-generated Image Detectioncited by 189
  5. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  6. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 113
  7. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  8. 2021Representative Forgery Mining for Fake Face Detectioncited by 108
  9. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 105
  10. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 91
  11. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 89
  12. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
38 more
  1. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  2. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 66
  3. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
  4. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  5. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  6. 2023Online Detection of AI-Generated Imagescited by 55
  7. 2022Deepfake Network Architecture Attributioncited by 47
  8. 2024LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detectioncited by 47
  9. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  10. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 44
  11. 2023Perceptual Artifacts Localization for Image Synthesis Taskscited by 43
  12. 2023GenDet: Towards Good Generalizations for AI-Generated Image Detectioncited by 36
  13. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36
  14. 2022Proactive Image Manipulation Detectioncited by 35
  15. 2023Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakescited by 31
  16. 2022GAN-generated Faces Detection: A Survey and New Perspectivescited by 30
  17. 2023MaLP: Manipulation Localization Using a Proactive Schemecited by 26
  18. 2022Discovering Transferable Forensic Features for CNN-generated Images Detectioncited by 24
  19. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  20. 2023A Representative Study on Human Detection of Artificially Generated Media Across Countriescited by 22
  21. 2024Beyond Deepfake Images: Detecting AI-Generated Videoscited by 22
  22. 2024Mixture of Low-rank Experts for Transferable AI-Generated Image Detectioncited by 21
  23. 2021Learning to Disentangle GAN Fingerprint for Fake Image Attributioncited by 20
  24. 2024ManiFPT: Defining and Analyzing Fingerprints of Generative Modelscited by 18
  25. 2023Improving Synthetically Generated Image Detection in Cross-Concept Settingscited by 15
  26. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  27. 2024Characteristics and prevalence of fake social media profiles with AI-generated facescited by 14
  28. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 13
  29. 2022AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fieldscited by 12
  30. 2025Methods and Trends in Detecting AI-Generated Images: A Comprehensive Reviewcited by 12
  31. 2021Forensic Analysis of Synthetically Generated Western Blot Imagescited by 11
  32. 2022D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensemblescited by 11
  33. 2025Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Imagescited by 11
  34. 2021Geo-DefakeHop: High-Performance Geographic Fake Image Detectioncited by 9
  35. 2025Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learningcited by 9
  36. 2023Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Networkcited by 8
  37. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  38. 2025Riemannian-Geometric Fingerprints of Generative Modelscited by 8

50 most cited of 124 All 124 (JSON)