Diffusion Noise Feature: Accurate and Fast Generated Image Detection

TL;DR

This paper introduces Diffusion Noise Feature (DNF), a novel representation derived from diffusion models that significantly improves the accuracy and robustness of detecting AI-generated images, even from unseen sources.

Contribution

The paper proposes DNF, a new feature based on diffusion model inverses, and demonstrates its effectiveness in enhancing generated image detection accuracy and generalization.

Findings

DNF achieves state-of-the-art detection accuracy.

DNF generalizes well to unseen generators.

The method is robust across multiple datasets.

Abstract

Generative models now produce images with such stunning realism that they can easily deceive the human eye. While this progress unlocks vast creative potential, it also presents significant risks, such as the spread of misinformation. Consequently, detecting generated images has become a critical research challenge. However, current detection methods are often plagued by low accuracy and poor generalization. In this paper, to address these limitations and enhance the detection of generated images, we propose a novel representation, Diffusion Noise Feature (DNF). Derived from the inverse process of diffusion models, DNF effectively amplifies the subtle, high-frequency artifacts that act as fingerprints of artificial generation. Our key insight is that real and generated images exhibit distinct DNF signatures, providing a robust basis for differentiation. By training a simple classifier such as ResNet-50 on DNF, our approach achieves remarkable accuracy, robustness, and generalization in detecting generated images, including those from unseen generators or with novel content. Extensive experiments across four training datasets and five test sets confirm that DNF establishes a new state-of-the-art in generated image detection. The code is available at https://github.com/YichiCS/Diffusion-Noise-Feature.