一种用于检测AI生成图像的双重差分方法
A Difference-in-Difference Approach to Detecting AI-Generated Images
把重建误差从一阶差分升级为二阶差分（difference-in-difference）来降低方差，这一思路可直接迁移到任何基于重建/残差信号的取证与异常检测流程中，例如扩散模型指纹检测或图像篡改定位。
原文依据 Instead of directly using the reconstruction error (a first-order difference), we compute the difference in reconstruction error -- a second-order difference
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散模型能够生成与真实图像几乎无法区分的AI生成图像，这引发了对其潜在滥用的担忧，并给检测这类图像带来了巨大挑战。许多现有检测器依赖重建误差——即输入图像与其重建版本之间的差异——作为区分真实图像与伪造图像的依据。然而，随着现代AI生成图像与真实图像日益相似，这些检测器的效果不断下降。为应对这一挑战，我们提出了一种新的双重差分方法。我们不再直接使用重建误差（一阶差分），而是计算重建误差的差异——即二阶差分——以降低方差并提升检测准确率。大量实验表明，我们的方法取得了很强的泛化性能，能够在生成式AI时代可靠地检测AI生成图像。代码见 https://github.com/Qixinyi1122-lucky/DID。
英文原文摘要 1042 字符
Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones, raising concerns about their potential misuse and posing 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. Code is available at https://github.com/Qixinyi1122-lucky/DID.