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

Recent advancements in image generation have provoked social and security concerns, yet most detection methods rely on black-box models that generalize poorly. By utilizing advances in Multi-modal Large Language Models (MLLMs), we propose a framework that fuses six specialized paradigms, each analyzing a distinct aspect of the image, to provide a final verdict with coherent, evidence-based reasoning. Experimental results on a diverse dataset of real and AIgenerated images demonstrate that our approach outperforms both traditional detection methods and top humans, while providing explainability. This study underscores the potential of MLLMs in developing robust, explainable, and reasoning-driven detection systems. The code is available at https://github.com/Gennadiyev/mllm- defake.