Saved in:
Bibliographic Details
Main Authors: Chu, Beilin, Xu, Xuan, Wang, Xin, Zhang, Yufei, You, Weike, Zhou, Linna
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.07140
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915590352928768
author Chu, Beilin
Xu, Xuan
Wang, Xin
Zhang, Yufei
You, Weike
Zhou, Linna
author_facet Chu, Beilin
Xu, Xuan
Wang, Xin
Zhang, Yufei
You, Weike
Zhou, Linna
contents The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guided Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07140
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error
Chu, Beilin
Xu, Xuan
Wang, Xin
Zhang, Yufei
You, Weike
Zhou, Linna
Computer Vision and Pattern Recognition
The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guided Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.
title FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.07140