Paper
19 July 2024 Local frequency analysis for diffusion-generated image detection
Jing Weng
Author Affiliations +
Proceedings Volume 13213, International Conference on Image Processing and Artificial Intelligence (ICIPAl 2024); 132130C (2024) https://doi.org/10.1117/12.3035198
Event: International Conference on Image Processing and Artificial Intelligence (ICIPAl2024), 2024, Suzhou, China
Abstract
With the development of generative adversarial networks (GANs) and diffusion models, deepfake has become a serious security issue. This study mainly aims to detect images produced by diffusion models. For this reason, this paper introduces an innovative Local Frequency Analysis (LFA) method which based on Krawchouk moment mesoscale frequency analysis and Discrete Cosine Transform (DCT) finescale frequency analysis, which simultaneously performs the frequency domain analysis of images from multi-scale to extract more comprehensive features. In this paper, experiments are performed on two datasets, GenImage and DiffusionForensics, and the proposed method is evaluated and contrasted against the existing methods. Also, the generalization capability of LFA for detecting forged images from different sources is experimented on the GenImage dataset. The results of the experiments show that LFA performs superiorly in detecting diffusion-generated images. In addition, robustness experiments on two types of degradation, JPEG compression and Gaussian blur, are also conducted to further demonstrate the practicality of LFA.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jing Weng "Local frequency analysis for diffusion-generated image detection", Proc. SPIE 13213, International Conference on Image Processing and Artificial Intelligence (ICIPAl 2024), 132130C (19 July 2024); https://doi.org/10.1117/12.3035198
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Diffusion

Image analysis

Performance modeling

Image quality

Data modeling

Image compression

Counterfeit detection

Back to Top