The reviewed record of science sign in
Pith

arxiv: 2410.02761 · v4 · pith:KCXZCFCQ · submitted 2024-10-03 · cs.CV · cs.AI

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

Zhipei Xu , Xuanyu Zhang , Runyi Li , Zecheng Tang , Qing Huang , Jian Zhang This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:KCXZCFCQrecord.jsonopen to challenge →

classification cs.CV cs.AI
keywords detectionfakeshieldforgeryexplainableifdlimagelocalizationmulti-modal
0
0 comments X
read the original abstract

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: \textbf{1)} black-box nature with unknown detection principle, \textbf{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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Toward Generalizable Forgery Detection and Reasoning

    cs.CV 2025-03 unverdicted novelty 7.0

    FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.

  2. Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection

    cs.CV 2026-06 unverdicted novelty 6.0

    VLMs for synthetic medical image detection overweight text metadata, flipping authenticity judgments on the same image and dropping accuracy on authentic images by 61.1% on average when an explicit AI-origin tag is present.

  3. When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing

    cs.CV 2026-06 unverdicted novelty 6.0

    Presents SPPE benchmark and ERMA/C2E-S2SER methods for editability assessment and surrogate-to-source recovery in MLLM privacy protection, reporting metric improvements.

  4. CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    Introduces a commercial-model contrastive AIGC video dataset and a hybrid contrastive-MLLM detection framework claiming SOTA performance on realistic video forgery detection.

  5. HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.

  6. Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning

    cs.CV 2025-12 unverdicted novelty 6.0

    Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.

  7. Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images

    cs.CV 2025-10 unverdicted novelty 6.0

    Locate-Then-Examine improves AI-generated image detection by localizing suspicious regions first then performing region-aware re-examination, while releasing the TRACE dataset of 20k annotated images.

  8. ImgEdit: A Unified Image Editing Dataset and Benchmark

    cs.CV 2025-05 conditional novelty 6.0

    ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.

  9. Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection

    cs.CV 2026-06 unverdicted novelty 5.0

    VLMs for synthetic medical image detection overweight accompanying metadata, as demonstrated by a new paired benchmark that fixes the image and varies controlled text variants across imaging modalities.

  10. Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection

    cs.CV 2026-05 unverdicted novelty 5.0

    Omni-Fake delivers a unified multimodal deepfake benchmark dataset and RL-driven detector that reports gains in accuracy, cross-modal generalization, and explainability over prior baselines.

  11. FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 4.0

    FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.