mlsanityData to 14 Oct 2026

FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

arXiv 2410.02761 ↗First posted 3 Oct 2024cs.CV cs.AIcited by 113

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

Abstract (arXiv)

The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect. Although current image forgery detection and localization (IFDL) methods are generally effective, they tend to face two challenges: 1) black-box nature with unknown detection principle, 2) limited generalization across diverse tampering methods (e.g., Photoshop, DeepFake, AIGC-Editing). To address these issues, we propose the explainable IFDL task and design FakeShield, a multi-modal framework capable of evaluating image authenticity, generating tampered region masks, and providing a judgment basis based on pixel-level and image-level tampering clues. Additionally, we leverage GPT-4o to enhance existing IFDL datasets, creating the Multi-Modal Tamper Description dataSet (MMTD-Set) for training FakeShield's tampering analysis capabilities. Meanwhile, we incorporate a Domain Tag-guided Explainable Forgery Detection Module (DTE-FDM) and a Multi-modal Forgery Localization Module (MFLM) to address various types of tamper detection interpretation and achieve forgery localization guided by detailed textual descriptions. Extensive experiments demonstrate that FakeShield effectively detects and localizes various tampering techniques, offering an explainable and superior solution compared to previous IFDL methods. The code is available at https://github.com/zhipeixu/FakeShield.

Key facts. Cited by 113 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 45 of its 74 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

45 of 74 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant19 Aug

Other references · 44

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2023Segment Anythingcited by 8,234
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  9. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  10. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  11. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  12. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
32 more
  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  2. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  3. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  4. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  5. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  6. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  7. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 455
  8. 2019On the Detection of Digital Face Manipulationcited by 260
  9. 2023DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Modelscited by 195
  10. 2023Hierarchical Fine-Grained Image Forgery Detection and Localizationcited by 134
  11. 2021PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localizationcited by 133
  12. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 123
  13. 2021MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detectioncited by 117
  14. 2021Image Manipulation Detection by Multi-View Multi-Scale Supervisioncited by 111
  15. 2023EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protectioncited by 111
  16. 2020SPAN: Spatial Pyramid Attention Network forImage Manipulation Localizationcited by 92
  17. 2023BianQue: Balancing the Questioning and Suggestion Ability of Health LLMs with Multi-turn Health Conversations Polished by ChatGPTcited by 65
  18. 2024Common Sense Reasoning for Deepfake Detectioncited by 65
  19. 2017Image Splicing Localization Using A Multi-Task Fully Convolutional Network (MFCN)cited by 64
  20. 2020DeepFake Detection Based on the Discrepancy Between the Face and its Contextcited by 56
  21. 2023CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganographycited by 50
  22. 2024Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detectioncited by 47
  23. 2022Detecting and Recovering Sequential DeepFake Manipulationcited by 34
  24. 2024V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protectioncited by 28
  25. 2023MaLP: Manipulation Localization Using a Proactive Schemecited by 26
  26. 2024GS-Hider: Hiding Messages into 3D Gaussian Splattingcited by 26
  27. 2022Learning to Immunize Images for Tamper Localization and Self-Recoverycited by 19
  28. 2021From Image to Imuge: Immunized Image Generationcited by 11
  29. 2023DRAW: Defending Camera-shooted RAW against Image Manipulationcited by 10
  30. 2021RWN: Robust Watermarking Network for Image Cropping Localizationcited by 9
  31. 2024Research about the Ability of LLM in the Tamper-Detection Areacited by 3
  32. 2024Protect-Your-IP: Scalable Source-Tracing and Attribution against Personalized Generationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 55; 2026: 53.

113 papers.

Sort:

By area:

  1. 2025ImgEdit: A Unified Image Editing Dataset and Benchmarkcited by 231
  2. 2024SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Modelcited by 108
  3. 2025Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanationcited by 68
  4. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
  5. 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizablecited by 60
  6. 2024OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarkingcited by 35
  7. 2025BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanationcited by 33
  8. 2025AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Modelscited by 33
  9. 2025BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLMcited by 29
  10. 2025Skyra: AI-Generated Video Detection via Grounded Artifact Reasoningcited by 25
  11. 2025FaceXBench: Evaluating Multimodal LLMs on Face Understandingcited by 24
  12. 2025Veritas: Generalizable Deepfake Detection via Pattern-Aware Reasoningcited by 23
38 more
  1. 2025Toward Generalizable Forgery Detection and Reasoningcited by 20
  2. 2025Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Modelscited by 19
  3. 2025VidGuard-R1: AI-Generated Video Detection and Explanation via Reasoning MLLMs and RLcited by 15
  4. 2025SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganographycited by 14
  5. 2024ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localizationcited by 13
  6. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  7. 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Modelscited by 12
  8. 2024ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detectioncited by 11
  9. 2025FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensicscited by 11
  10. 2025UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localizationcited by 9
  11. 2025MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generationcited by 9
  12. 2025Rethinking Cross-Generator Image Forgery Detection through DINOv3cited by 8
  13. 2026Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detectioncited by 8
  14. 2026Venus-DeFakerOne: Unified Fake Image Detection & Localizationcited by 8
  15. 2025DiffDoctor: Diagnosing Image Diffusion Models Before Treatingcited by 7
  16. 2025Explainable Synthetic Image Detection through Diffusion Timestep Ensemblingcited by 7
  17. 2025Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakescited by 7
  18. 2025FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Modelscited by 6
  19. 2025AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detectioncited by 6
  20. 2025ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attackcited by 6
  21. 2026TextShield-R1: Reinforced Reasoning for Tampered Text Detectioncited by 6
  22. 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulationcited by 6
  23. 2026EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detectioncited by 6
  24. 2025So-Fake: Benchmarking and Explaining Social Media Image Forgery Detectioncited by 5
  25. 2025PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detectioncited by 5
  26. 2025ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanationcited by 5
  27. 2025REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detectioncited by 5
  28. 2026Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervisioncited by 5
  29. 2025GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Modelcited by 4
  30. 2025Towards Reliable Identification of Diffusion-based Image Manipulationscited by 4
  31. 2025Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Imagescited by 4
  32. 2025TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detectioncited by 4
  33. 2025Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detectioncited by 4
  34. 2026GPT4o-Receipt: A Dataset and Human Study for AI-Generated Document Forensicscited by 4
  35. 2026FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detectioncited by 4
  36. 2026MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentationcited by 4
  37. 2025Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotationcited by 3
  38. 2026TalkPhoto: A Versatile Training-Free Conversational Assistant for Intelligent Image Editingcited by 3

50 most cited of 113 All 113 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model
  2. 2025Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics
  3. 2024TGIF: Text-Guided Inpainting Forgery Dataset
  4. 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
  5. 2024EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM
  6. 2025Towards Explainable Fake Image Detection with Multi-Modal Large Language Models
  7. 2025REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language
  8. 2025Explainable Detection of AI-Generated Images with Artifact Localization Using Faster-Than-Lies and Vision-Language Models for Edge Devices