dorsal/arxiv
View SchemaR$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images
| Authors | Qingyu Liu, Zhongjie Ba, Jianmin Guo, Qiu Wang, Zhibo Wang, Jie Shi, Kui Ren |
|---|---|
| Categories | |
| ArXiv ID | 2601.08867vv1 |
| URL | https://arxiv.org/abs/2601.08867 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
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$^2$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$+$ steps. Extensive experiments on the benchmark from 10 public datasets demonstrate that R$^2$BD is over 22$\times$ 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. The code and dataset used for evaluation are available at https://github.com/QingyuLiu/RRBD.
{
"annotation_id": "6b6f7136-883d-400d-90d9-a1bb3dd2fdf9",
"date_created": "2026-02-17T05:53:20.289000Z",
"date_modified": "2026-02-17T05:53:20.289000Z",
"file_hash": "a50a22e9cc7a07893cf24e3b529ba9a8022c7a0d632534e30ba04556222358ea",
"private": false,
"record": {
"abstract": "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.\n In this paper, we propose a novel fake image detection framework, called R$^2$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$+$ steps.\n Extensive experiments on the benchmark from 10 public datasets demonstrate that R$^2$BD is over 22$\\times$ 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. The code and dataset used for evaluation are available at https://github.com/QingyuLiu/RRBD.",
"arxiv_id": "2601.08867",
"authors": [
"Qingyu Liu",
"Zhongjie Ba",
"Jianmin Guo",
"Qiu Wang",
"Zhibo Wang",
"Jie Shi",
"Kui Ren"
],
"categories": [
"cs.CV",
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images",
"url": "https://arxiv.org/abs/2601.08867",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "9d4609a3-0e41-4444-87b5-b137390172d5",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}