R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909989803655168 |
|---|---|
| author | Liu, Qingyu Ba, Zhongjie Guo, Jianmin Wang, Qiu Wang, Zhibo Shi, Jie Ren, Kui |
| author_facet | Liu, Qingyu Ba, Zhongjie Guo, Jianmin Wang, Qiu Wang, Zhibo Shi, Jie Ren, Kui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08867 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images Liu, Qingyu Ba, Zhongjie Guo, Jianmin Wang, Qiu Wang, Zhibo Shi, Jie Ren, Kui Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.08867 |