R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images

2026-01-11

AI Summary

This work addresses the inefficiency and limited generalizability of existing reconstruction-based methods for detecting forged images, particularly their poor performance on non-diffusion generative models such as GANs. To overcome these limitations, the authors propose the R²BD framework, which introduces a unified G-LDM reconstruction model capable of simultaneously emulating the generation behaviors of VAEs, GANs, and diffusion models. A key innovation is the single-step residual bias computation module, enabling efficient discrimination between real and forged images within a single inference pass. Evaluated across ten public datasets, the proposed method achieves a speedup of over 22× compared to current reconstruction-based approaches and improves average cross-dataset detection accuracy by 13.87%, substantially enhancing both generalization capability and practical applicability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

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.

Problem

• fake image detection
• reconstruction-based methods
• generalization
• efficiency
• generative models

Innovation

• reconstruction-based detection
• generalizable fake image detection
• unified generative modeling
• single-step inference
• residual bias