Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce reasoning texts that suffer from hallucinations and overthinking. To address this, we propose ForgerySleuth, which leverages M-LLMs to perform comprehensive clue fusion and generate segmentation outputs indicating specific regions that are tampered with. Moreover, we construct the ForgeryAnalysis dataset through the Chain-of-Clues prompt, which includes analysis and reasoning text to upgrade the image manipulation detection task. A data engine is also introduced to build a larger-scale dataset for the pre-training phase. Our extensive experiments demonstrate the effectiveness of ForgeryAnalysis and show that ForgerySleuth significantly outperforms existing methods in generalization, robustness, and explainability.
@article{arxiv.2411.19466,
title = {ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection},
author = {Zhihao Sun and Haoran Jiang and Haoran Chen and Yixin Cao and Xipeng Qiu and Zuxuan Wu and Yu-Gang Jiang},
journal= {arXiv preprint arXiv:2411.19466},
year = {2025}
}