Generalizable Detection of AI Generated Images with Large Models and Fuzzy Decision Tree

TL;DR

This paper introduces a novel detection framework combining lightweight artifact detectors with multimodal large language models through a fuzzy decision tree, achieving state-of-the-art accuracy in identifying AI-generated images.

Contribution

The work presents a new fusion approach that integrates semantic reasoning and perceptual artifact detection using a fuzzy decision tree, enhancing generalization and accuracy.

Findings

Achieves state-of-the-art detection accuracy.

Demonstrates strong generalization across diverse models.

Effectively combines semantic and perceptual cues.

Abstract

The malicious use and widespread dissemination of AI-generated images pose a serious threat to the authenticity of digital content. Existing detection methods exploit low-level artifacts left by common manipulation steps within the generation pipeline, but they often lack generalization due to model-specific overfitting. Recently, researchers have resorted to Multimodal Large Language Models (MLLMs) for AIGC detection, leveraging their high-level semantic reasoning and broad generalization capabilities. While promising, MLLMs lack the fine-grained perceptual sensitivity to subtle generation artifacts, making them inadequate as standalone detectors. To address this issue, we propose a novel AI-generated image detection framework that synergistically integrates lightweight artifact-aware detectors with MLLMs via a fuzzy decision tree. The decision tree treats the outputs of basic detectors as fuzzy membership values, enabling adaptive fusion of complementary cues from semantic and perceptual perspectives. Extensive experiments demonstrate that the proposed method achieves state-of-the-art accuracy and strong generalization across diverse generative models.