---
title: "Fast and Generalizable AI-Generated Image Detection via Model-Agnostic Feature Reconstruction"
authors:
  - "Qinghui He"
  - "Haifeng Zhang"
  - "Bo Liu"
  - "Yang Wei"
doi: "10.24963/ijcai.2026/131"
url: "https://ijcai.org/proceedings/2026/131"
pdf: "https://ijcai.org/proceedings/2026/0131.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1170-1178"
track: "Main Track"
keywords:
  - "Computer Vision: Recognition (object detection, categorization)"
---

# Fast and Generalizable AI-Generated Image Detection via Model-Agnostic Feature Reconstruction

Qinghui He, Haifeng Zhang, Bo Liu, Yang Wei

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1170-1178. DOI: [10.24963/ijcai.2026/131](https://doi.org/10.24963/ijcai.2026/131)

## Abstract

Generative models continue to advance rapidly in both fidelity and diversity, posing increasing challenges for reliably distinguishing generated images from real ones. Existing reconstruction-based detection methods often rely on assumptions tied to specific generative models, which leads to limited cross-model generalization and substantial computational overhead. In this paper, we propose General Feature Reconstruction Error (GFRE), a fast and generalizable detection paradigm that leverages reconstruction behavior in a general-purpose representation space. Our key insight is that real and generated images exhibit consistently different reconstruction stability when projected into universal visual representations. Instead of tracing generator-specific artifacts, GFRE employs a lightweight autoencoder to model the reconstructability of image representations, producing a reconstruction signal that is inherently generator-agnostic and transferable across diverse generative processes. Extensive experiments on images synthesized by 18 different generative models demonstrate that GFRE consistently outperforms existing state-of-the-art methods, achieving a 4.70% improvement in detection accuracy and an 8.20% gain in cross-model generalization. Moreover, by avoiding costly generator inversion and diffusion-based reconstruction, GFRE reduces reconstruction error extraction time by up to 150x, enabling efficient and scalable deployment.