mlsanityData to 14 Oct 2026

On the detection of synthetic images generated by diffusion models

arXiv 2211.00680 ↗First posted 1 Nov 2022cs.CVcited by 283

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

Abstract (arXiv)

Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code are available at github.com/grip-unina/DMimageDetection.

Key facts. Cited by 283 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 23 of its 34 references that are in the map. First posted on arXiv 1 Nov 2022.

Builds on

23 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 21

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  9. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  10. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  11. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  12. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
9 more
  1. 2020What makes fake images detectable? Understanding properties that generalizecited by 273
  2. 2020Media Forensics and DeepFakes: an overviewcited by 209
  3. 2018Do GANs leave artificial fingerprints?cited by 190
  4. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  5. 2018Noiseprint: a CNN-based camera model fingerprintcited by 114
  6. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  7. 2022Detecting GAN-generated Images by Orthogonal Training of Multiple CNNscited by 46
  8. 2022Lighting (In)consistency of Paint by Textcited by 35
  9. 2022Perspective (In)consistency of Paint by Textcited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 42; 2024: 93; 2025: 72; 2026: 74.

283 papers.

Sort:

By area:

  1. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  2. 2023Zero-shot Image-to-Image Translationcited by 505
  3. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  4. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
  5. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 265
  6. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
  7. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  8. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  9. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 125
  10. 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 123
  11. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 108
  12. 2024DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmarkcited by 92
38 more
  1. 2024Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detectioncited by 89
  2. 2023CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Imagescited by 84
  3. 2023Evading Watermark based Detection of AI-Generated Contentcited by 78
  4. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76
  5. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 69
  6. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanationcited by 68
  7. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  8. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  9. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  10. 2024LightIt: Illumination Modeling and Control for Diffusion Modelscited by 57
  11. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 57
  12. 2023Online Detection of AI-Generated Imagescited by 55
  13. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited 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. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 49
  17. 2023Exposing the Fake: Effective Diffusion-Generated Images Detectioncited by 48
  18. 2024LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detectioncited by 47
  19. 2023AutoSplice: A Text-prompt Manipulated Image Dataset for Media Forensicscited by 46
  20. 2024D3: Scaling Up Deepfake Detection by Learning from Discrepancycited by 45
  21. 2024IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localizationcited by 42
  22. 2024Diffusion Facial Forgery Detectioncited by 41
  23. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  24. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  25. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36
  26. 2024Aligned Datasets Improve Detection of Latent Diffusion-Generated Imagescited by 36
  27. 2023ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detectioncited by 35
  28. 2025D3: Training-Free AI-Generated Video Detection Using Second-Order Featurescited by 34
  29. 2024WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detectioncited by 31
  30. 2023Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysiscited by 30
  31. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  32. 2025BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLMcited by 29
  33. 2024AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmarkcited by 28
  34. 2024LaWa: Using Latent Space for In-Generation Image Watermarkingcited by 28
  35. 2023Nepotistically Trained Generative-AI Models Collapsecited by 27
  36. 2024Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similaritiescited by 27
  37. 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?cited by 26
  38. 2022GLFF: Global and Local Feature Fusion for AI-synthesized Image Detectioncited by 25

50 most cited of 283 All 283 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2022Towards the Detection of Diffusion Model Deepfakes
  2. 2025Beyond Binary Classification: A Semi-supervised Approach to Generalized AI-generated Image Detection
  3. 2025Toward Generalized Detection of Synthetic Media: Limitations, Challenges, and the Path to Multimodal Solutions
  4. 2024StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model
  5. 2026Repurposing Image Diffusion Models for Adversarial Synthetic Structured Data: A Case Study of Ground Truth Drift
  6. 2025Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach
  7. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
  8. 2025Who Made This? Fake Detection and Source Attribution with Diffusion Features