mlsanityData to 14 Oct 2026

Exposing the Fake: Effective Diffusion-Generated Images Detection

arXiv 2307.06272 ↗First posted 12 Jul 2023cs.CV cs.CR cs.LGcited by 48

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

Abstract (arXiv)

Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, there is a dearth of research dedicated to detecting diffusion-generated images, which could pose potential security and privacy risks. This paper addresses this gap by proposing a novel detection method called Stepwise Error for Diffusion-generated Image Detection (SeDID). Comprising statistical-based SeDIDStat and neural network-based SeDIDNNs, SeDID exploits the unique attributes of diffusion models, namely deterministic reverse and deterministic denoising computation errors. Our evaluations demonstrate SeDID's superior performance over existing methods when applied to diffusion models. Thus, our work makes a pivotal contribution to distinguishing diffusion model-generated images, marking a significant step in the domain of artificial intelligence security.

Key facts. Cited by 48 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 33 of its 41 references that are in the map. First posted on arXiv 12 Jul 2023.

Builds on

33 of 41 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023DIRE for Diffusion-Generated Image Detection16 Mar
  2. 2022On the detection of synthetic images generated by diffusion models1 Nov
  3. 2022Towards the Detection of Diffusion Model Deepfakes26 Oct
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2022Generative Adversarial Networkscited by 5,627
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  11. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
16 more
  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  2. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  3. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  4. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  5. 2020Label-Only Membership Inference Attackscited by 388
  6. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  7. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  8. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 233
  9. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 182
  10. 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?cited by 136
  11. 2023Membership Inference Attacks against Diffusion Modelscited by 86
  12. 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 78
  13. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 70
  14. 2023An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initializationcited by 54
  15. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  16. 2020Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AIcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 22; 2025: 17; 2026: 9.

48 papers.

Sort:

By area:

  1. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 125
  2. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76
  3. 2024LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detectioncited by 47
  4. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 47
  5. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  6. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  7. 2025ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localizationcited by 22
  8. 2024Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videoscited by 21
  9. 2024Bi-LORA: A Vision-Language Approach for Synthetic Image Detectioncited by 20
  10. 2024Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Imagescited by 20
  11. 2024Are CLIP features all you need for Universal Synthetic Image Origin Attribution?cited by 14
  12. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Imagescited by 14
36 more
  1. 2024A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authenticationcited by 13
  2. 2025Few-Shot Learner Generalizes Across AI-Generated Image Detectioncited by 13
  3. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  4. 2025LOTA: Bit-Planes Guided AI-Generated Image Detectioncited by 11
  5. 2024HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated imagescited by 9
  6. 2024Harnessing the Power of Large Vision Language Models for Synthetic Image Detectioncited by 7
  7. 2025Explainable Synthetic Image Detection through Diffusion Timestep Ensemblingcited by 7
  8. 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challengescited by 6
  9. 2024Artifact Feature Purification for Cross-domain Detection of AI-generated Imagescited by 5
  10. 2024Improving Interpretability and Robustness for the Detection of AI-Generated Imagescited by 5
  11. 2024UGAD: Universal Generative AI Detector utilizing Frequency Fingerprintscited by 5
  12. 2025LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detectioncited by 5
  13. 2024A Comprehensive Survey on Diffusion Models and Their Applicationscited by 4
  14. 2024The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methodscited by 4
  15. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  16. 2025Rethinking Individual Fairness in Deepfake Detectioncited by 4
  17. 2025Noise-Informed Diffusion-Generated Image Detection with Anomaly Attentioncited by 3
  18. 2025FakeParts: a New Family of AI-Generated DeepFakescited by 3
  19. 2026Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detectioncited by 3
  20. 2024FIDAVL: Fake Image Detection and Attribution using Vision-Language Modelcited by 2
  21. 2024Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image Detectioncited by 2
  22. 2024EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLMcited by 2
  23. 2025Rethinking the Use of Vision Transformers for AI-Generated Image Detectioncited by 2
  24. 2026A Difference-in-Difference Approach to Detecting AI-Generated Imagescited by 2
  25. 2025End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detectioncited by 1
  26. 2025EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shiftcited by 1
  27. 2026Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Imagescited by 1
  28. 2026Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detectioncited by 1
  29. 2025HRR: Hierarchical Retrospection Refinement for Generated Image Detectioncited by 0
  30. 2025Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetectcited by 0
  31. 2025Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learningcited by 0
  32. 2026Color Matters: Demosaicing-Guided Color Correlation Training for Generalizable AI-Generated Image Detectioncited by 0
  33. 2026Deepfake Detection Generalization with Diffusion Noisecited by 0
  34. 2026AI-Generated Images: What Humans and Machines See When They Look at the Same Imagecited by 0
  35. 2026Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII)cited by 0
  36. 2026GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion Noise Feature: Accurate and Fast Generated Image Detection
  2. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
  3. 2026FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection
  4. 2024Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
  5. 2024Anomaly detection using Diffusion-based methods
  6. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey
  7. 2024TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
  8. 2024Detecting AutoEncoder is Enough to Catch LDM Generated Images