mlsanityData to 14 Oct 2026

FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies

arXiv 2509.20890 ↗First posted 25 Sep 2025cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

The increasing realism of synthetic images generated by advanced models such as VAEs, GANs, and LDMs poses significant challenges for synthetic image detection. To address this issue, we explore two artifact types introduced during the generation process: (1) latent distribution deviations and (2) decoding-induced smoothing effects, which manifest as inconsistencies in local textures, edges, and color transitions. Leveraging local pixel dependencies (LPD) properties rooted in Markov Random Fields, we reconstruct synthetic images using neighboring pixel information to expose disruptions in texture continuity and edge coherence. Building upon LPD, we propose FerretNet, a lightweight neural network with only 1.1M parameters that delivers efficient and robust synthetic image detection. Extensive experiments demonstrate that FerretNet, trained exclusively on the 4-class ProGAN dataset, achieves an average accuracy of 97.1% on an open-world benchmark comprising 22 generative models. Our code and datasets are publicly available at https://github.com/xigua7105/FerretNet.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

48 of 56 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  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. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  10. 2022Scalable Diffusion Models with Transformerscited by 6,054
  11. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
36 more
  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  10. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  12. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  13. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  14. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  15. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  16. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  17. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  18. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 523
  19. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  20. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  21. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  22. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 280
  23. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 182
  24. 2024CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Modelscited by 149
  25. 2024Golden Noise for Diffusion Models: A Learning Frameworkcited by 92
  26. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 89
  27. 2019Preventing Posterior Collapse with delta-VAEscited by 86
  28. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  29. 2024FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modificationcited by 64
  30. 2021BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detectioncited by 60
  31. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  32. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
  33. 2020Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Spacecited by 34
  34. 2023Complexity Matters: Rethinking the Latent Space for Generative Modelingcited by 19
  35. 2023Discrepancy-Guided Reconstruction Learning for Image Forgery Detectioncited by 7
  36. 2023Towards Robust GAN-generated Image Detection: a Multi-view Completion Representationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 10.

12 papers.

  1. 2025Scaling Up AI-Generated Image Detection with Generator-Aware Prototypescited by 9
  2. 2026SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoderscited by 2
  3. 2025INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifactscited by 1
  4. 2026RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetrycited by 1
  5. 2026Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detectioncited by 1
  6. 2026DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detectioncited by 1
  7. 2026Dissect and Prune: Enhancing Robustness in AI-Generated Image Detectioncited by 1
  8. 2026CTForensics: A Comprehensive Dataset and Method for AI-Generated CT Image Detectioncited by 0
  9. 2026Adaptive Forensic Feature Refinement via Intrinsic Importance Perceptioncited by 0
  10. 2026LEGO: LoRA-Enabled Generator-Oriented Framework for Synthetic Image Detectioncited by 0
  11. 2026Certification of Real Images through Calibrated Content Authenticationcited by 0
  12. 2026COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detectioncited by 0