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

TL;DR

This paper introduces a novel difference-in-difference method that enhances detection of AI-generated images by analyzing second-order differences in reconstruction error, improving robustness against increasingly realistic AI images.

Contribution

The paper proposes a new difference-in-difference approach that significantly improves detection accuracy and generalization for AI-generated images compared to existing methods.

Findings

Achieves high detection accuracy across diverse AI-generated images

Demonstrates robustness against advanced diffusion models

Outperforms traditional reconstruction error-based detectors

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.