Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: 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.
Authors (6)
Beilin Chu
Xuan Xu
Xin Wang
Yufei Zhang
Weike You
Linna Zhou
Submitted
December 10, 2024
Key Contributions
This paper introduces FIRE, a novel method for detecting diffusion-generated images by analyzing reconstruction errors in mid-band frequencies. It is the first to investigate frequency decomposition's influence on reconstruction error, offering a robust approach that generalizes to unseen diffusion models and maintains robustness against diversions.
Business Value
Enables reliable verification of image authenticity, crucial for combating misinformation, ensuring evidence integrity in legal contexts, and protecting brand reputation from counterfeit media.