Research

Paper

AI LLM February 27, 2026

A Difference-in-Difference Approach to Detecting AI-Generated Images

Authors

Xinyi Qi, Kai Ye, Chengchun Shi, Ying Yang, Hongyi Zhou, Jin Zhu

Abstract

Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones. This raises concerns about their potential misuse and poses substantial challenges for detecting them. Many existing detectors rely on reconstruction error -- the difference between the input image and its reconstructed version -- as the basis for distinguishing real from fake images. However, these detectors become less effective as modern AI-generated images become increasingly similar to real ones. To address this challenge, we propose a novel difference-in-difference method. Instead of directly using the reconstruction error (a first-order difference), we compute the difference in reconstruction error -- a second-order difference -- for variance reduction and improving detection accuracy. Extensive experiments demonstrate that our method achieves strong generalization performance, enabling reliable detection of AI-generated images in the era of generative AI.

Metadata

arXiv ID: 2602.23732
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.23732v1</id>\n    <title>A Difference-in-Difference Approach to Detecting AI-Generated Images</title>\n    <updated>2026-02-27T06:57:39Z</updated>\n    <link href='https://arxiv.org/abs/2602.23732v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.23732v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones. This raises concerns about their potential misuse and poses substantial challenges for detecting them. Many existing detectors rely on reconstruction error -- the difference between the input image and its reconstructed version -- as the basis for distinguishing real from fake images. However, these detectors become less effective as modern AI-generated images become increasingly similar to real ones. To address this challenge, we propose a novel difference-in-difference method. Instead of directly using the reconstruction error (a first-order difference), we compute the difference in reconstruction error -- a second-order difference -- for variance reduction and improving detection accuracy. Extensive experiments demonstrate that our method achieves strong generalization performance, enabling reliable detection of AI-generated images in the era of generative AI.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-27T06:57:39Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Xinyi Qi</name>\n    </author>\n    <author>\n      <name>Kai Ye</name>\n    </author>\n    <author>\n      <name>Chengchun Shi</name>\n    </author>\n    <author>\n      <name>Ying Yang</name>\n    </author>\n    <author>\n      <name>Hongyi Zhou</name>\n    </author>\n    <author>\n      <name>Jin Zhu</name>\n    </author>\n  </entry>"
}