mlsanityData to 14 Oct 2026

FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error

arXiv 2412.07140 ↗First posted 10 Dec 2024cs.CVcited by 47

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guided Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 39 of its 51 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

39 of 51 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss5 Jan
  2. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  3. 2022Pseudo Numerical Methods for Diffusion Models on Manifolds20 Feb
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  5. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesis29 Nov
  6. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  7. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  5. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  8. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  9. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  10. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  11. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  12. 2023InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuningcited by 345
19 more
  1. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 125
  2. 2023PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detectioncited by 122
  3. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 99
  4. 2020Responsible Disclosure of Generative Models Using Scalable Fingerprintingcited by 91
  5. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensicscited by 69
  6. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectorscited by 64
  7. 2024FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusioncited by 61
  8. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
  9. 2021ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Imagescited by 48
  10. 2023Exposing the Fake: Effective Diffusion-Generated Images Detectioncited by 48
  11. 2024FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledgecited by 48
  12. 2024Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detectioncited by 47
  13. 2024LaRE2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detectioncited by 47
  14. 2024RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detectioncited by 36
  15. 2024Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similaritiescited by 27
  16. 2024Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detectioncited by 24
  17. 2024Frequency Masking for Universal Deepfake Detectioncited by 23
  18. 2023Diffusion Noise Feature: Accurate and Fast Generated Image Detectioncited by 21
  19. 2023Kandinsky 3.0 Technical Reportcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 22; 2026: 25.

47 papers.

Sort:

By area:

  1. 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizablecited by 60
  2. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  3. 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentationcited by 23
  4. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  5. 2025Robust Single-Stage Fully Sparse 3D Object Detection via Detachable Latent Diffusioncited by 12
  6. 2025NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detectioncited by 8
  7. 2025LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detectioncited by 5
  8. 2025DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detectioncited by 5
  9. 2025Fully AI-Generated Image Detection: Definition, Recent Advances and Challengescited by 4
  10. 2025Towards Reliable Identification of Diffusion-based Image Manipulationscited by 4
  11. 2025AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignmentcited by 4
  12. 2025Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detectioncited by 4
35 more
  1. 2026Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detectioncited by 4
  2. 2025Noise-Informed Diffusion-Generated Image Detection with Anomaly Attentioncited by 3
  3. 2025When Semantics Regulate: Rethinking Patch Shuffle and Internal Bias for Generated Image Detection with CLIPcited by 3
  4. 2026Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Modelscited by 3
  5. 2025Semantic-Aware Reconstruction Error for Detecting AI-Generated Imagescited by 2
  6. 2025UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localizationcited by 2
  7. 2026A Difference-in-Difference Approach to Detecting AI-Generated Imagescited by 2
  8. 2026ForensicConcept: Transferable Forensic Concepts for AIGI Detectioncited by 2
  9. 2025Revealing the Implicit Noise-based Imprint of Generative Modelscited by 1
  10. 2025End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detectioncited by 1
  11. 2025PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Imagescited by 1
  12. 2025NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localizationcited by 1
  13. 2026GRRE: Leveraging G-Channel Removed Reconstruction Error for Robust Detection of AI-Generated Imagescited by 1
  14. 2026Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Imagescited by 1
  15. 2026Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detectioncited by 1
  16. 2026Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detectioncited by 1
  17. 2026Spectral Tail Auxiliary Learning for AI-Generated Image Detectioncited by 1
  18. 2026HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detectioncited by 1
  19. 2026DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detectioncited by 1
  20. 2026Dissect and Prune: Enhancing Robustness in AI-Generated Image Detectioncited by 1
  21. 2025Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approachcited by 0
  22. 2025How Noise Benefits AI-generated Image Detectioncited by 0
  23. 2026S^2F-Net:A Robust Spatial-Spectral Fusion Framework for Cross-Model AIGC Detectioncited by 0
  24. 2026RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detectioncited by 0
  25. 2026Efficient Zero-Shot AI-Generated Image Detectioncited by 0
  26. 2026CIPHER: Counterfeit Image Pattern High-level Examination via Representationcited by 0
  27. 2026Detecting Diffusion-generated Images via Dynamic Assembly Forestscited by 0
  28. 2026HiMix: Hierarchical Artifact-aware Mixup for Generalized Synthetic Image Detectioncited by 0
  29. 2026CHROMA: Detecting AI-Generated Images through Inter-Channel Color-Space Correlationscited by 0
  30. 2026LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residualscited by 0
  31. 2026Beyond Natural Images: Rethinking AI-Generated Image Detection in Documentscited by 0
  32. 2026Frequency-Domain AI-Generated Image Detection: Exploring Decoder and Channel Attention for Feature Refinementcited by 0
  33. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0
  34. 2026RED: Reconstruction Evolution Dynamics for Generalizable AI-Generated Image Detectioncited by 0
  35. 2026Certification of Real Images through Calibrated Content Authenticationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Frequency Forgery Clues for Diffusion-Generated Image Detection
  2. 2022Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
  3. 2024FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
  4. 2024Boosting Diffusion Models with Moving Average Sampling in Frequency Domain
  5. 2025Preserving Spectral Structure and Statistics in Diffusion Models
  6. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
  7. 2025A Fourier Space Perspective on Diffusion Models
  8. 2024Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration