mlsanityData to 7 Oct 2026

FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion

arXiv 2406.08603 ↗First posted 12 Jun 2024cs.CV cs.AI cs.LGcited by 61

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

Abstract (arXiv)

Due to the high potential for abuse of GenAI systems, the task of detecting synthetic images has recently become of great interest to the research community. Unfortunately, existing image-space detectors quickly become obsolete as new high-fidelity text-to-image models are developed at blinding speed. In this work, we propose a new synthetic image detector that uses features obtained by inverting an open-source pre-trained Stable Diffusion model. We show that these inversion features enable our detector to generalize well to unseen generators of high visual fidelity (e.g., DALL-E 3) even when the detector is trained only on lower fidelity fake images generated via Stable Diffusion. This detector achieves new state-of-the-art across multiple training and evaluation setups. Moreover, we introduce a new challenging evaluation protocol that uses reverse image search to mitigate stylistic and thematic biases in the detector evaluation. We show that the resulting evaluation scores align well with detectors' in-the-wild performance, and release these datasets as public benchmarks for future research.

Key facts. Cited by 61 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 39 of its 51 references that are in the map. First posted on arXiv 12 Jun 2024.

Builds on

39 of 51 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation27 Feb
  2. 2023DIRE for Diffusion-Generated Image Detection16 Mar
  3. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  4. 2022On the detection of synthetic images generated by diffusion models1 Nov
  5. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models26 Oct
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  11. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
20 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  4. 2018Demystifying MMD GANscited by 1,268
  5. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  6. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  7. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  8. 2023Zero-shot Image-to-Image Translationcited by 503
  9. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  10. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  11. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  12. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  13. 2020What makes fake images detectable? Understanding properties that generalizecited by 272
  14. 2018Do GANs leave artificial fingerprints?cited by 188
  15. 2019Seeing What a GAN Cannot Generatecited by 148
  16. 2019XRAI: Better Attributions Through Regionscited by 116
  17. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  18. 2015How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?cited by 76
  19. 2023Online Detection of AI-Generated Imagescited by 55
  20. 2024Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Losscited by 51

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 32; 2026: 22.

61 papers.

Sort:

By area:

  1. 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
  2. 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizablecited by 58
  3. 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
  4. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 46
  5. 2025Generating Multi-Image Synthetic Data for Text-to-Image Customizationcited by 25
  6. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  7. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  8. 2025Toward Generalizable Forgery Detection and Reasoningcited by 20
  9. 2025Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detectioncited by 16
  10. 2025Few-Shot Learner Generalizes Across AI-Generated Image Detectioncited by 13
  11. 2025Learning an Image Editing Model without Image Editing Pairscited by 13
  12. 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detectioncited by 10
38 more
  1. 2024Evolution of Detection Performance throughout the Online Lifespan of Synthetic Imagescited by 8
  2. 2026Venus-DeFakerOne: Unified Fake Image Detection & Localizationcited by 7
  3. 2026Improving Robotic Generalist Policies via Flow Reversal Steeringcited by 5
  4. 2025SFLD: Reducing the content bias for AI-generated Image Detectioncited by 4
  5. 2025Fully AI-Generated Image Detection: Definition, Recent Advances and Challengescited by 4
  6. 2025RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectorscited by 4
  7. 2025Towards Reliable Identification of Diffusion-based Image Manipulationscited by 4
  8. 2025DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detectioncited by 4
  9. 2026Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detectioncited by 4
  10. 2026Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detectioncited by 4
  11. 2024Present and Future Generalization of Synthetic Image Detectorscited by 3
  12. 2025X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Modelscited by 3
  13. 2025When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIPcited by 3
  14. 2024Time Step Generating: A Universal Synthesized Deepfake Image Detectorcited by 2
  15. 2025A Data-Driven Diffusion-based Approach for Audio Deepfake Explanationscited by 2
  16. 2025Semantic-Aware Reconstruction Error for Detecting AI-Generated Imagescited by 2
  17. 2025Who Made This? Fake Detection and Source Attribution with Diffusion Featurescited by 2
  18. 2025Generalized Design Choices for Deepfake Detectorscited by 2
  19. 2025Rethinking the Use of Vision Transformers for AI-Generated Image Detectioncited by 2
  20. 2025Robust and Calibrated Detection of Authentic Multimedia Contentcited by 2
  21. 2026A Difference-in-Difference Approach to Detecting AI-Generated Imagescited by 2
  22. 2025GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detectioncited by 1
  23. 2025End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detectioncited by 1
  24. 2025UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localizationcited by 1
  25. 2025PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Imagescited by 1
  26. 2026GRRE: Leveraging G-Channel Removed Reconstruction Error for Robust Detection of AI-Generated Imagescited by 1
  27. 2026A Marketplace for AI-Generated Adult Content and Deepfakescited by 1
  28. 2026Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detectioncited by 1
  29. 2026HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detectioncited by 1
  30. 2026BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectorscited by 1
  31. 2024Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Modelscited by 0
  32. 2025HRR: Hierarchical Retrospection Refinement for Generated Image Detectioncited by 0
  33. 2025Fooling the Watchers: Breaking AIGC Detectors via Semantic Prompt Attackscited by 0
  34. 2025MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillationcited by 0
  35. 2025Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetectcited by 0
  36. 2025Security Risk of Misalignment between Text and Image in Multi-modal Modelcited by 0
  37. 2025How Noise Benefits AI-generated Image Detectioncited by 0
  38. 2026Color Matters: Demosaicing-Guided Color Correlation Training for Generalizable AI-Generated Image Detectioncited by 0

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Detecting Origin Attribution for Text-to-Image Diffusion Models
  2. 2025Explainable Synthetic Image Detection through Diffusion Timestep Ensembling
  3. 2024Aligned Datasets Improve Detection of Latent Diffusion-Generated Images
  4. 2026R2BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images
  5. 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
  6. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
  7. 2025Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach
  8. 2026When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators