Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection

TL;DR

This paper introduces a dual frequency branch framework with reconstructed sliding windows attention to improve the detection of AI-generated images, enhancing generalization across various generative models.

Contribution

It proposes a novel dual frequency domain framework combined with local feature reconstruction to better capture forgery traces in AI-generated images.

Findings

Achieves 2.13% higher detection accuracy than state-of-the-art methods.

Effective in detecting images from 65 different generative models.

Enhances generalization capability across GAN and diffusion model-based images.

Abstract

The rapid advancement of Generative Adversarial Networks (GANs) and diffusion models has enabled the creation of highly realistic synthetic images, presenting significant societal risks, such as misinformation and deception. As a result, detecting AI-generated images has emerged as a critical challenge. Existing researches emphasize extracting fine-grained features to enhance detector generalization, yet they often lack consideration for the importance and interdependencies of internal elements within local regions and are limited to a single frequency domain, hindering the capture of general forgery traces. To overcome the aforementioned limitations, we first utilize a sliding window to restrict the attention mechanism to a local window, and reconstruct the features within the window to model the relationships between neighboring internal elements within the local region. Then, we design a dual frequency domain branch framework consisting of four frequency domain subbands of DWT and the phase part of FFT to enrich the extraction of local forgery features from different perspectives. Through feature enrichment of dual frequency domain branches and fine-grained feature extraction of reconstruction sliding window attention, our method achieves superior generalization detection capabilities on both GAN and diffusion model-based generative images. Evaluated on diverse datasets comprising images from 65 distinct generative models, our approach achieves a 2.13\% improvement in detection accuracy over state-of-the-art methods.