mlsanityData to 7 Oct 2026

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

arXiv 2503.14905 ↗First posted 19 Mar 2025cs.CVcited by 66

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challenges for authenticity assessment and detection. Despite the effectiveness of existing methods in evaluating image authenticity and locating forgeries, these approaches often lack human interpretability and do not fully address the growing complexity of synthetic data. To tackle these challenges, we introduce FakeVLM, a specialized large multimodal model designed for both general synthetic image and DeepFake detection tasks. FakeVLM not only excels in distinguishing real from fake images but also provides clear, natural language explanations for image artifacts, enhancing interpretability. Additionally, we present FakeClue, a comprehensive dataset containing over 100,000 images across seven categories, annotated with fine-grained artifact clues in natural language. FakeVLM demonstrates performance comparable to expert models while eliminating the need for additional classifiers, making it a robust solution for synthetic data detection. Extensive evaluations across multiple datasets confirm the superiority of FakeVLM in both authenticity classification and artifact explanation tasks, setting a new benchmark for synthetic image detection. The code, model weights, and dataset can be found here: https://github.com/opendatalab/FakeVLM.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 61 of its 87 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

61 of 87 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model5 Dec
  2. 2024LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models13 Oct
  3. 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models3 Oct
  4. 2024FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant19 Aug
  5. 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics21 Mar
  6. 2023AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors26 Oct

Other references · 55

  1. 2017Attention Is All You Needcited by 59,932
  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. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  9. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  11. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
38 more
  1. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  2. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  3. 2024DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understandingcited by 559
  4. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
  5. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  6. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  7. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  8. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  9. 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
  10. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 286
  11. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  12. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  13. 2020VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrievalcited by 188
  14. 2024A Sanity Check for AI-generated Image Detectioncited by 187
  15. 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 185
  16. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  17. 2020Learning Self-Consistency for Deepfake Detectioncited by 179
  18. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 162
  19. 2025Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters Morecited by 149
  20. 2024Why are Visually-Grounded Language Models Bad at Image Classification?cited by 101
  21. 2023Detecting and Grounding Multi-Modal Media Manipulationcited by 98
  22. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  23. 2025Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?cited by 76
  24. 2019SRM : A Style-based Recalibration Module for Convolutional Neural Networkscited by 65
  25. 2024Common Sense Reasoning for Deepfake Detectioncited by 64
  26. 2023Detecting and Grounding Multi-Modal Media Manipulation and Beyondcited by 55
  27. 2024Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?cited by 52
  28. 2023M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysiscited by 44
  29. 2023Perceptual Artifacts Localization for Image Synthesis Taskscited by 43
  30. 2020CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysiscited by 42
  31. 2024Cross-view image geo-localization with Panorama-BEV Co-Retrieval Networkcited by 40
  32. 2024Where am I? Cross-View Geo-localization with Natural Language Descriptionscited by 38
  33. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  34. 2024Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detectioncited by 30
  35. 2024UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarioscited by 28
  36. 2024CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesiscited by 23
  37. 2024As Good As A Coin Toss: Human detection of AI-generated images, videos, audio, and audiovisual stimulicited by 22
  38. 2023Detecting Generated Images by Real Images Onlycited by 20

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 27; 2026: 39.

66 papers.

Sort:

By area:

  1. 2025GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generationcited by 57
  2. 2026Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perceptioncited by 47
  3. 2025Ivy-Fake: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detectioncited by 34
  4. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  5. 2025BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLMcited by 28
  6. 2025Skyra: AI-Generated Video Detection via Grounded Artifact Reasoningcited by 24
  7. 2025Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoningcited by 23
  8. 2025Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detectioncited by 19
  9. 2025FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensicscited by 11
  10. 2025RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewardscited by 11
  11. 2026GenClaw: Code-Driven Agentic Image Generationcited by 10
  12. 2025UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localizationcited by 9
38 more
  1. 2025BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perceptioncited by 9
  2. 2025MIRAGE: Towards AI-Generated Image Detection in the Wildcited by 8
  3. 2025Scaling Up AI-Generated Image Detection with Generator-Aware Prototypescited by 8
  4. 2026Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detectioncited by 8
  5. 2025Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakescited by 7
  6. 2025ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detectioncited by 7
  7. 2025Semantic Visual Anomaly Detection and Reasoning in AI-Generated Imagescited by 7
  8. 2026Venus-DeFakerOne: Unified Fake Image Detection & Localizationcited by 7
  9. 2026EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detectioncited by 6
  10. 2025So-Fake: Benchmarking and Explaining Social Media Image Forgery Detectioncited by 4
  11. 2025Towards Reliable Identification of Diffusion-based Image Manipulationscited by 4
  12. 2025MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generationcited by 4
  13. 2025Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Imagescited by 4
  14. 2025TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detectioncited by 4
  15. 2026Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalitiescited by 4
  16. 2025FakeParts: a New Family of AI-Generated DeepFakescited by 3
  17. 2025AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignmentcited by 3
  18. 2026Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detectioncited by 3
  19. 2026VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detectioncited by 3
  20. 2026AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detectioncited by 3
  21. 2026UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detectioncited by 3
  22. 2026FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detectioncited by 3
  23. 2026Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Modelscited by 3
  24. 2025DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflectioncited by 2
  25. 2025OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learningcited by 2
  26. 2026Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detectioncited by 2
  27. 2026Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detectioncited by 2
  28. 2025METER: Multi-modal Evidence-based Thinking and Explainable Reasoning -- Algorithm and Benchmarkcited by 1
  29. 2025AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMscited by 1
  30. 2026Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidancecited by 1
  31. 2026LOGER: Local--Global Ensemble for Robust Deepfake Detection in the Wildcited by 1
  32. 2026AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Imagescited by 1
  33. 2026EditSleuth: A Dataset of Grounded Reasoning Chains for Image-Edit Forensicscited by 1
  34. 2026GenShield: Unified Detection and Artifact Correction for AI-Generated Imagescited by 1
  35. 2026XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detectioncited by 1
  36. 2026ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Modelscited by 0
  37. 2026M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detectioncited by 0
  38. 2026OmniVL-Guard Pro: A Tool-Augmented Agent for Omnibus Vision-Language Forensicscited by 0

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
  2. 2025Explainable Detection of AI-Generated Images with Artifact Localization Using Faster-Than-Lies and Vision-Language Models for Edge Devices
  3. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detection
  4. 2024Synthetic Photography Detection: A Visual Guidance for Identifying Synthetic Images Created by AI
  5. 2025Identity-Aware Vision-Language Model for Explainable Face Forgery Detection
  6. 2025VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systems
  7. 2024Harnessing the Power of Large Vision Language Models for Synthetic Image Detection
  8. 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models