GRRE: Leveraging G-Channel Removed Reconstruction Error for Robust Detection of AI-Generated Images

2026-01-06

arXiv.org

AI Summary

This work addresses the limited generalization of existing AI-generated image detection methods when confronted with novel or unseen generative models. The authors propose a lightweight detection paradigm based on Green-channel Removal Reconstruction Error (GRRE), which leverages a previously unexploited discriminative cue: the significant discrepancy in reconstruction error between real and AI-generated images after removal of the green channel. This approach requires no complex training; instead, it achieves robust detection solely through channel removal and reconstruction error analysis. Extensive experiments demonstrate that the method consistently outperforms state-of-the-art techniques across a wide range of both known and previously unseen generative models, substantially enhancing cross-model generalization and resilience to perturbations.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Efficient ML / Green AI
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

The rapid progress of generative models, particularly diffusion models and GANs, has greatly increased the difficulty of distinguishing synthetic images from real ones. Although numerous detection methods have been proposed, their accuracy often degrades when applied to images generated by novel or unseen generative models, highlighting the challenge of achieving strong generalization. To address this challenge, we introduce a novel detection paradigm based on channel removal reconstruction. Specifically, we observe that when the green (G) channel is removed from real images and reconstructed, the resulting reconstruction errors differ significantly from those of AI-generated images. Building upon this insight, we propose G-channel Removed Reconstruction Error (GRRE), a simple yet effective method that exploits this discrepancy for robust AI-generated image detection. Extensive experiments demonstrate that GRRE consistently achieves high detection accuracy across multiple generative models, including those unseen during training. Compared with existing approaches, GRRE not only maintains strong robustness against various perturbations and post-processing operations but also exhibits superior cross-model generalization. These results highlight the potential of channel-removal-based reconstruction as a powerful forensic tool for safeguarding image authenticity in the era of generative AI.

Problem

• AI-generated image detection
• generalization
• robustness
• generative models
• image forensics

Innovation

• GRRE
• channel removal
• reconstruction error
• AI-generated image detection
• cross-model generalization