EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift

TL;DR

EIRES introduces a training-free image detection method that exploits structural edit-induced reconstruction error shifts to distinguish real images from AI-generated ones, enhancing security and privacy.

Contribution

The paper presents EIRES, a novel training-free approach leveraging structural edits to detect AI-generated images based on error shifts, without requiring model training.

Findings

Effective across diverse generative models

Robust against post-processing operations

No training needed, relies on natural signal separability

Abstract

Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding: structural edits enhance the reconstruction of real images while degrading that of generated images, creating a distinctive edit-induced reconstruction error shift. This asymmetric shift enhances the separability between real and generated images. Building on this insight, we propose EIRES, a training-free method that leverages structural edits to reveal inherent differences between real and generated images. To explain the discriminative power of this shift, we derive the reconstruction error lower bound under edit perturbations. Since EIRES requires no training, thresholding depends solely on the natural separability of the signal, where a larger margin yields more reliable detection. Extensive experiments show that EIRES is effective across diverse generative models and remains robust on the unbiased subset, even under post-processing operations.