通过检测自编码器痕迹，无需训练即可识别扩散模型生成图像
Detecting AutoEncoder is Enough to Catch LDM Generated Images
- 利用自编码器重建痕迹作为检测信号
- 在真实与重建图像间区分准确率高，误报极少
- 无需合成数据训练，适合快速部署防伪系统
近年来，扩散模型已成为图像生成的主要方法之一。然而，检测此类模型生成的图像仍具挑战性。本文提出一种新方法，通过识别潜在扩散模型（LDM）自编码器引入的伪影来检测生成图像。通过训练分类器区分真实图像与由LDM自编码器重建的图像，该方法可在不直接使用生成图像训练的情况下实现检测。研究新颖性在于：不同于以往方法，本方案无需合成数据训练，显著降低计算成本并提升泛化能力。实验表明，该方法具备高检测准确率且误报率极低，是应对虚假图像的有力工具。
原文摘要 · Abstract (English)
In recent years, diffusion models have become one of the main methods for generating images. However, detecting images generated by these models remains a challenging task. This paper proposes a novel method for detecting images generated by Latent Diffusion Models (LDM) by identifying artifacts introduced by their autoencoders. By training a detector to distinguish between real images and those reconstructed by the LDM autoencoder, the method enables detection of generated images without directly training on them. The novelty of this research lies in the fact that, unlike similar approaches, this method does not require training on synthesized data, significantly reducing computational costs and enhancing generalization ability. Experimental results show high detection accuracy with minimal false positives, making this approach a promising tool for combating fake images.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。