mlsanityData to 7 Oct 2026

DIRE for Diffusion-Generated Image Detection

arXiv 2303.09295 ↗First posted 16 Mar 2023cs.CVcited by 386

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

Abstract (arXiv)

Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a detector for telling apart real images from diffusion-generated images. We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data. To address this issue, we propose a novel image representation called DIffusion Reconstruction Error (DIRE), which measures the error between an input image and its reconstruction counterpart by a pre-trained diffusion model. We observe that diffusion-generated images can be approximately reconstructed by a diffusion model while real images cannot. It provides a hint that DIRE can serve as a bridge to distinguish generated and real images. DIRE provides an effective way to detect images generated by most diffusion models, and it is general for detecting generated images from unseen diffusion models and robust to various perturbations. Furthermore, we establish a comprehensive diffusion-generated benchmark including images generated by eight diffusion models to evaluate the performance of diffusion-generated image detectors. Extensive experiments on our collected benchmark demonstrate that DIRE exhibits superiority over previous generated-image detectors. The code and dataset are available at https://github.com/ZhendongWang6/DIRE.

Key facts. Cited by 386 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 46 of its 53 references that are in the map. First posted on arXiv 16 Mar 2023.

Builds on

46 of 53 references.

Closest ancestors · 7

Same direction, newest first

  1. 2022On the detection of synthetic images generated by diffusion models1 Nov
  2. 2022Towards the Detection of Diffusion Model Deepfakes26 Oct
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec
  7. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov

Other references · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
27 more
  1. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  6. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  9. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  10. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  11. 2023Extracting Training Data from Diffusion Modelscited by 723
  12. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  13. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 518
  14. 2023Zero-shot Image-to-Image Translationcited by 503
  15. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  16. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  17. 2022Detecting Deepfakes with Self-Blended Imagescited by 332
  18. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  19. 2020What makes fake images detectable? Understanding properties that generalizecited by 272
  20. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 208
  21. 2018Do GANs leave artificial fingerprints?cited by 188
  22. 2018Learning Rich Features for Image Manipulation Detectioncited by 154
  23. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  24. 2018Detecting GAN-generated Imagery using Color Cuescited by 75
  25. 2019Detecting Photoshopped Faces by Scripting Photoshopcited by 55
  26. 2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
  27. 2023Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacycited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 18; 2024: 101; 2025: 136; 2026: 131.

386 papers.

Sort:

By area:

  1. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  2. 2024BLINK: Multimodal Large Language Models Can See but Not Perceivecited by 529
  3. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  4. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  5. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  6. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  7. 2024DF40: Toward Next-Generation Deepfake Detectioncited by 126
  8. 2024VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Modelscited by 124
  9. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
  10. 2023PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detectioncited by 119
  11. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 107
  12. 2024Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detectioncited by 102
38 more
  1. 2024Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspectivecited by 88
  2. 2024DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmarkcited by 85
  3. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 73
  4. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  5. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  6. 2023Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for nowcited by 61
  7. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  8. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
  9. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  10. 2024Real-Time Deepfake Detection in the Real-Worldcited by 49
  11. 2025Is Artificial Intelligence Generated Image Detection a Solved Problem?cited by 49
  12. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 48
  13. 2023Exposing the Fake: Effective Diffusion-Generated Images Detectioncited by 48
  14. 2024LCM-Lookahead for Encoder-based Text-to-Image Personalizationcited by 48
  15. 2024CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detectioncited by 47
  16. 2024LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detectioncited by 47
  17. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 46
  18. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  19. 2024A Single Simple Patch is All You Need for AI-generated Image Detectioncited by 43
  20. 2024Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasetscited by 43
  21. 2024D3: Scaling Up Deepfake Detection by Learning from Discrepancycited by 43
  22. 2024DiP-GO: A Diffusion Pruner via Few-step Gradient Optimizationcited by 43
  23. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
  24. 2024Diffusion Facial Forgery Detectioncited by 41
  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. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  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. 2025Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detectioncited by 34
  34. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  35. 2025D3: Training-Free AI-Generated Video Detection Using Second-Order Featurescited by 32
  36. 2024WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detectioncited by 31
  37. 2025BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanationcited by 30
  38. 2024DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysiscited by 29

50 most cited of 386 All 386 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models in Low-Level Vision: A Survey
  2. 2025Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models
  3. 2025Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach
  4. 2022Diffusion Models in Vision: A Survey
  5. 2024Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image Detection
  6. 2023Masked Diffusion Models Are Fast Distribution Learners
  7. 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
  8. 2023One-step Diffusion with Distribution Matching Distillation