mlsanityData to 7 Oct 2026

A Sanity Check for AI-generated Image Detection

arXiv 2406.19435 ↗First posted 27 Jun 2024cs.CVcited by 187

Not on the map. Why?

Cited by 29 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With the rapid development of generative models, discerning AI-generated content has evoked increasing attention from both industry and academia. In this paper, we conduct a sanity check on "whether the task of AI-generated image detection has been solved". To start with, we present Chameleon dataset, consisting AIgenerated images that are genuinely challenging for human perception. To quantify the generalization of existing methods, we evaluate 9 off-the-shelf AI-generated image detectors on Chameleon dataset. Upon analysis, almost all models classify AI-generated images as real ones. Later, we propose AIDE (AI-generated Image DEtector with Hybrid Features), which leverages multiple experts to simultaneously extract visual artifacts and noise patterns. Specifically, to capture the high-level semantics, we utilize CLIP to compute the visual embedding. This effectively enables the model to discern AI-generated images based on semantics or contextual information; Secondly, we select the highest frequency patches and the lowest frequency patches in the image, and compute the low-level patchwise features, aiming to detect AI-generated images by low-level artifacts, for example, noise pattern, anti-aliasing, etc. While evaluating on existing benchmarks, for example, AIGCDetectBenchmark and GenImage, AIDE achieves +3.5% and +4.6% improvements to state-of-the-art methods, and on our proposed challenging Chameleon benchmarks, it also achieves the promising results, despite this problem for detecting AI-generated images is far from being solved.

Key facts. Cited by 187 papers in the map (data through 7 Oct 2026). Builds on 50 of its 65 references that are in the map. First posted on arXiv 27 Jun 2024.

Builds on

50 of 65 references.

References · 50

  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. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2020Denoising Diffusion Implicit Modelscited by 9,655
  10. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  11. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  12. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
38 more
  1. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  2. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  12. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  13. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  14. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  15. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  16. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  17. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  18. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  19. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  20. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  21. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 376
  22. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  23. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  24. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  25. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  26. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  27. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  28. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  29. 2023CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Imagescited by 84
  30. 2018Detecting GAN-generated Imagery using Color Cuescited by 75
  31. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  32. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 43
  33. 2024Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasetscited by 43
  34. 2023GenDet: Towards Good Generalizations for AI-Generated Image Detectioncited by 36
  35. 2023ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detectioncited by 35
  36. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  37. 2024WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detectioncited by 31
  38. 2023Diffusion Noise Feature: Accurate and Fast Generated Image Detectioncited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 80; 2026: 100.

187 papers.

Sort:

By area:

  1. 2025OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generationcited 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. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
  5. 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizablecited by 58
  6. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
  7. 2024LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Modelscited by 51
  8. 2025Is Artificial Intelligence Generated Image Detection a Solved Problem?cited by 49
  9. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
  10. 2025Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detectioncited by 34
  11. 2025SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Modelscited by 33
  12. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
38 more
  1. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?cited by 33
  2. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  3. 2025All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learningcited by 23
  4. 2025Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoningcited by 23
  5. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  6. 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Maskingcited by 21
  7. 2025Toward Generalizable Forgery Detection and Reasoningcited by 20
  8. 2025Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detectioncited by 19
  9. 2026NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wildcited by 18
  10. 2025Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approachcited by 16
  11. 2025Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detectioncited by 16
  12. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  13. 2025Methods and Trends in Detecting AI-Generated Images: A Comprehensive Reviewcited by 12
  14. 2025FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensicscited by 11
  15. 2025CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanismscited by 11
  16. 2026VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learningcited by 11
  17. 2025Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detectioncited by 10
  18. 2025Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detectioncited by 10
  19. 2024HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated imagescited by 9
  20. 2025UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localizationcited by 9
  21. 2025Training-free Detection of AI-generated images via Cropping Robustnesscited by 9
  22. 2024Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Modelscited by 8
  23. 2025NTIRE 2025 challenge on Text to Image Generation Model Quality Assessmentcited by 8
  24. 2025Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?cited by 8
  25. 2025Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learningcited by 8
  26. 2025MIRAGE: Towards AI-Generated Image Detection in the Wildcited by 8
  27. 2025Rethinking Cross-Generator Image Forgery Detection through DINOv3cited by 8
  28. 2025Scaling Up AI-Generated Image Detection with Generator-Aware Prototypescited by 8
  29. 2026Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detectioncited by 8
  30. 2025NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detectioncited by 7
  31. 2026Venus-DeFakerOne: Unified Fake Image Detection & Localizationcited by 7
  32. 2024Adversarial Robustness of AI-Generated Image Detectors in the Real Worldcited by 6
  33. 2025AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detectioncited by 6
  34. 2025Few-Shot Synthetic Image Attribution: Identifying Unseen Generators with Limited Samplescited by 6
  35. 2026Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Modelscited by 6
  36. 2026EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detectioncited by 6
  37. 2025Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detectioncited by 5
  38. 2025LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detectioncited by 5

50 most cited of 187 All 187 (JSON)