mlsanityData to 7 Oct 2026

Towards Universal Fake Image Detectors that Generalize Across Generative Models

arXiv 2302.10174 ↗First posted 20 Feb 2023cs.CV cs.LGcited by 483

Not on the map. Why?

Cited by 68 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With generative models proliferating at a rapid rate, there is a growing need for general purpose fake image detectors. In this work, we first show that the existing paradigm, which consists of training a deep network for real-vs-fake classification, fails to detect fake images from newer breeds of generative models when trained to detect GAN fake images. Upon analysis, we find that the resulting classifier is asymmetrically tuned to detect patterns that make an image fake. The real class becomes a sink class holding anything that is not fake, including generated images from models not accessible during training. Building upon this discovery, we propose to perform real-vs-fake classification without learning; i.e., using a feature space not explicitly trained to distinguish real from fake images. We use nearest neighbor and linear probing as instantiations of this idea. When given access to the feature space of a large pretrained vision-language model, the very simple baseline of nearest neighbor classification has surprisingly good generalization ability in detecting fake images from a wide variety of generative models; e.g., it improves upon the SoTA by +15.07 mAP and +25.90% acc when tested on unseen diffusion and autoregressive models.

Key facts. Cited by 483 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 20 Feb 2023.

Builds on

35 of 49 references.

References · 35

  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. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
23 more
  1. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  4. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  5. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  6. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  7. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  8. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  9. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  10. 2018Learning to See in the Darkcited by 459
  11. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  12. 2020What makes fake images detectable? Understanding properties that generalizecited by 272
  13. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  14. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  15. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  16. 2018ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detectioncited by 104
  17. 2018Diverse Image Synthesis from Semantic Layouts via Conditional IMLEcited by 60
  18. 2017Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detectioncited by 56
  19. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  20. 2020Frequency Domain Image Translation: More Photo-realistic, Better Identity-preservingcited by 46
  21. 2022Proactive Image Manipulation Detectioncited by 35
  22. 2019MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generationcited by 29
  23. 2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 98; 2025: 171; 2026: 194.

483 papers.

Sort:

By area:

  1. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  2. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  3. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  4. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 124
  5. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  6. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
  7. 2023PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detectioncited by 119
  8. 2024C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detectioncited by 111
  9. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  10. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
  11. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  12. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 88
38 more
  1. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  2. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  3. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanationcited by 66
  4. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 65
  5. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
  6. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  7. 2024MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMscited by 60
  8. 2024AVFF: Audio-Visual Feature Fusion for Video Deepfake Detectioncited by 59
  9. 2024Exploiting Style Latent Flows for Generalizing Deepfake Video Detectioncited by 58
  10. 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizablecited by 58
  11. 2025GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generationcited by 57
  12. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
  13. 2023Online Detection of AI-Generated Imagescited by 55
  14. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  15. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  16. 2024Real-Time Deepfake Detection in the Real-Worldcited by 49
  17. 2025Is Artificial Intelligence Generated Image Detection a Solved Problem?cited by 49
  18. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  19. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  20. 2023Perceptual Artifacts Localization for Image Synthesis Taskscited by 43
  21. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 43
  22. 2024Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasetscited by 43
  23. 2024D3: Scaling Up Deepfake Detection by Learning from Discrepancycited by 43
  24. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
  25. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  26. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 40
  27. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 38
  28. 2024Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Modelcited by 37
  29. 2023GenDet: Towards Good Generalizations for AI-Generated Image Detectioncited by 36
  30. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  31. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36
  32. 2024Aligned Datasets Improve Detection of Latent Diffusion-Generated Imagescited by 36
  33. 2025AI-Generated Video Detection via Perceptual Straighteningcited by 34
  34. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  35. 2024Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakescited by 32
  36. 2025D3: Training-Free AI-Generated Video Detection Using Second-Order Featurescited by 32
  37. 2024Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detectioncited by 30
  38. 2025BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanationcited by 30

50 most cited of 483 All 483 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
  2. 2026R2BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images
  3. 2023Improving Synthetically Generated Image Detection in Cross-Concept Settings
  4. 2023Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis
  5. 2022Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs
  6. 2023Improving the Effectiveness of Deep Generative Data
  7. 2023A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
  8. 2023Real-Fake: Effective Training Data Synthesis Through Distribution Matching