mlsanityData to 7 Oct 2026

Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics

arXiv 2403.14077 ↗First posted 21 Mar 2024cs.AI cs.CRcited by 68

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

Abstract (arXiv)

DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation. Detecting DeepFakes is currently solved with programmed machine learning algorithms. In this work, we investigate the capabilities of multimodal large language models (LLMs) in DeepFake detection. We conducted qualitative and quantitative experiments to demonstrate multimodal LLMs and show that they can expose AI-generated images through careful experimental design and prompt engineering. This is interesting, considering that LLMs are not inherently tailored for media forensic tasks, and the process does not require programming. We discuss the limitations of multimodal LLMs for these tasks and suggest possible improvements.

Key facts. Cited by 68 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 31 of its 46 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

31 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models6 Feb

Other references · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  10. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  11. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  12. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 573
18 more
  1. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
  2. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  3. 2018Exposing DeepFake Videos By Detecting Face Warping Artifactscited by 318
  4. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  5. 2018Capsule-Forensics: Using Capsule Networks to Detect Forged Images and Videoscited by 180
  6. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  7. 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
  8. 2023Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosiscited by 77
  9. 2018Detecting GAN-generated Imagery using Color Cuescited by 75
  10. 2020Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlightscited by 59
  11. 2021Beyond the Spectrum: Detecting Deepfakes via Re-Synthesiscited by 44
  12. 2022Explaining Deepfake Detection by Analysing Image Matchingcited by 34
  13. 2024How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainabilitycited by 33
  14. 2019Exposing GAN-synthesized Faces Using Landmark Locationscited by 30
  15. 2020How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signalscited by 29
  16. 2021Wavelet-Packets for Deepfake Image Analysis and Detectioncited by 25
  17. 2022GLFF: Global and Local Feature Fusion for AI-synthesized Image Detectioncited by 25
  18. 2023ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknowncited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 34; 2026: 18.

68 papers.

Sort:

By area:

  1. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanationcited by 66
  2. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 57
  3. 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?cited by 48
  4. 2024FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Errorcited by 46
  5. 2024DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Expertscited by 42
  6. 2025Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detectorcited by 38
  7. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Modelscited by 36
  8. 2024X2-DFD: A framework for eXplainable and eXtendable Deepfake Detectioncited by 35
  9. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  10. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  11. 2025ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detectioncited by 17
  12. 2025Characterizing Photorealism and Artifacts in Diffusion Model-Generated Imagescited by 13
38 more
  1. 2025Exploring ChatGPT for Face Presentation Attack Detection in Zero and Few-Shot in-Context Learningcited by 12
  2. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  3. 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Modelscited by 12
  4. 2025OpenFake: An Open Dataset and Platform Toward Real-World Deepfake Detectioncited by 9
  5. 2025A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localizationcited by 8
  6. 2024Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixturecited by 7
  7. 2025Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakescited by 7
  8. 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challengescited by 6
  9. 2025REVEAL: Robust Evolution of Vision-Language Models for Explainable AI-Video Detectioncited by 6
  10. 2026EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detectioncited by 6
  11. 2024How Good is ChatGPT at Audiovisual Deepfake Detection: A Comparative Study of ChatGPT, AI Models and Human Perceptioncited by 5
  12. 2025Benchmarking Multimodal Large Language Models for Face Recognitioncited by 5
  13. 2025From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detectioncited by 5
  14. 2024Multimodal Chain-of-Thought Reasoning via ChatGPT to Protect Children from Age-Inappropriate Appscited by 4
  15. 2024A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoningcited by 4
  16. 2024Human Action CLIPs: Detecting AI-generated Human Motioncited by 4
  17. 2025Who Owns the Output? Bridging Law and Technology in LLMs Attributioncited by 4
  18. 2025ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Modelscited by 4
  19. 2025REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detectioncited by 4
  20. 2026GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensicscited by 4
  21. 2024URSimulator: Human-Perception-Driven Prompt Tuning for Enhanced Virtual Urban Renewal via Diffusion Modelscited by 3
  22. 2024HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAscited by 3
  23. 2025LLMs Are Not Yet Ready for Deepfake Image Detectioncited by 3
  24. 2025Weakly Supervised Multimodal Temporal Forgery Localization via Multitask Learningcited by 3
  25. 2025AlignGemini: Generalizable AI-Generated Image Detection Through Task-Model Alignmentcited by 3
  26. 2026Evaluating Multimodal Large Language Models for Heterogeneous Face Recognitioncited by 3
  27. 2026VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detectioncited by 3
  28. 2026FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detectioncited by 3
  29. 2026Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Modelscited by 3
  30. 2025Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samplescited by 2
  31. 2025Visual Language Models as Zero-Shot Deepfake Detectorscited by 2
  32. 2025DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflectioncited by 2
  33. 2025Human Re-ID Meets LVLMs: What can we expect?cited by 1
  34. 2025Identity-Aware Vision-Language Model for Explainable Face Forgery Detectioncited by 1
  35. 2025Performance Decay in Deepfake Detection: The Limitations of Training on Outdated Datacited by 1
  36. 2025A parameter-efficient three-branch architecture for multimodal misinformation detection with limited annotationscited by 1
  37. 2026Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detectioncited by 1
  38. 2026Emergent Morphing Attack Detection in Open Multi-modal Large Language Modelscited by 1

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics
  2. 2025Can Multi-modal (reasoning) LLMs work as deepfake detectors?
  3. 2025SynthGuard: An Open Platform for Detecting AI-Generated Multimedia with Multimodal LLMs
  4. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images
  5. 2025Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection
  6. 2026Leveraging large multimodal models for audio-video deepfake detection: a pilot study
  7. 2025Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoning
  8. 2025EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning