mlsanityData to 14 Oct 2026

Towards Explainable Fake Image Detection with Multi-Modal Large Language Models

arXiv 2504.14245 ↗First posted 19 Apr 2025cs.CV cs.CLcited by 8

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

Abstract (arXiv)

Progress in image generation raises significant public security concerns. We argue that fake image detection should not operate as a "black box". Instead, an ideal approach must ensure both strong generalization and transparency. Recent progress in Multi-modal Large Language Models (MLLMs) offers new opportunities for reasoning-based AI-generated image detection. In this work, we evaluate the capabilities of MLLMs in comparison to traditional detection methods and human evaluators, highlighting their strengths and limitations. Furthermore, we design six distinct prompts and propose a framework that integrates these prompts to develop a more robust, explainable, and reasoning-driven detection system. The code is available at https://github.com/Gennadiyev/mllm-defake.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 47 of its 77 references that are in the map. First posted on arXiv 19 Apr 2025.

Builds on

47 of 77 references.

References · 47

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  10. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  11. 2017Neural Discrete Representation Learningcited by 4,712
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
35 more
  1. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  2. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,462
  9. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  10. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  12. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  13. 2023VILA: On Pre-training for Visual Language Modelscited by 692
  14. 2023mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaborationcited by 547
  15. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  16. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  17. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 482
  18. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 454
  19. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  20. 2020What makes fake images detectable? Understanding properties that generalizecited by 273
  21. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 227
  22. 2020Global Texture Enhancement for Fake Face Detection in the Wildcited by 220
  23. 2024MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIcited by 193
  24. 2023MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learningcited by 172
  25. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 139
  26. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 125
  27. 2024Common Sense Reasoning for Deepfake Detectioncited by 65
  28. 2024Community Forensics: Using Thousands of Generators to Train Fake Image Detectorscited by 50
  29. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  30. 2024Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasetscited by 43
  31. 2024VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Informationcited by 39
  32. 2023Detecting Generated Images by Real Images Onlycited by 20
  33. 2025Toward Generalizable Forgery Detection and Reasoningcited by 20
  34. 2023Situating the social issues of image generation models in the model life cycle: a sociotechnical approachcited by 9
  35. 2024AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detectioncited by 7
  2. 2026EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detectioncited by 6
  3. 2025From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detectioncited by 5
  4. 2025Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Imagescited by 4
  5. 2025AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignmentcited by 4
  6. 2026VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detectioncited by 3
  7. 2025Explainable AI-Generated Image Detection RewardBenchcited by 0
  8. 2026Beyond Semantics: Uncovering the Physics of Fakes via Universal Physical Descriptors for Cross-Modal Synthetic Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection
  2. 2025Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
  3. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
  4. 2026Generalizable Detection of AI Generated Images with Large Models and Fuzzy Decision Tree
  5. 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
  6. 2024Harnessing the Power of Large Vision Language Models for Synthetic Image Detection
  7. 2026UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models
  8. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation