.png){kind=icon}
.png){kind=icon}
Return
R<sup>2</sup>BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images
.png){kind=icon}
PRE
AI
Q
Z
J
Q
王
J
K
DOI：10.1109/tdsc.2026.3692527.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, reconstruction-based methods have gained attention for AIGC image detection. These methods leverage pre-trained diffusion models to reconstruct inputs and measure residuals for distinguishing real from fake images. Their key advantage lies in reducing reliance on dataset-specific artifacts and improving generalization under distribution shifts. However, they are limited by significant inefficiency due to multi-step inversion and reconstruction, and their reliance on diffusion backbones further limits generalization to other generative paradigms such as GANs. In this paper, we propose a novel fake image detection framework, called R<inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula>BD, built upon two key designs: 1) G-LDM, a unified reconstruction model that simulates the generation behaviors of VAEs, GANs, and diffusion models, thereby broadening the detection scope beyond prior diffusion-only approaches; and 2) a residual bias calculation module that distinguishes real and fake images in a single inference step, which is a significant efficiency improvement over existing methods that typically require 20<inline-formula><tex-math notation="LaTeX">$+$</tex-math></inline-formula> steps. Extensive experiments on the benchmark from 10 public datasets demonstrate that R<inline-formula><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula>BD is over 22× faster than existing reconstruction-based methods while achieving superior detection accuracy. In cross-dataset evaluations, it outperforms state-of-the-art methods by an average of 13.87%, showing strong efficiency and generalization across diverse generative methods.
Keywords:
AIGC detection
deepfake detection
diffusion model
GAN
Journal
IF:
7.5
Papers:
2.4K
Citations:
9.6K
Organization
Cited Papers