Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for malicious purposes. In this paper, we propose using the lightweight multi Local Intrinsic Dimensionality (multiLID), which has been originally developed in context of the detection of adversarial examples, for the automatic detection of synthetic images and the identification of the according generator networks. In contrast to many existing detection approaches, which often only work for GAN-generated images, the proposed method provides close to perfect detection results in many realistic use cases. Extensive experiments on known and newly created datasets demonstrate that multiLID exhibits superiority in diffusion detection and model identification. Since the empirical evaluations of recent publications on the detection of generated images is often too focused on the "LSUN-Bedroom" dataset, we further establish a comprehensive benchmark for the detection of diffusion-generated images, including samples from several diffusion models with different image sizes to evaluate the performance of their multiLID. Code for our experiments is provided at https://github.com/deepfake-study/deepfake_multiLID.

翻译：扩散模型近期已被成功应用于生成视觉上高度逼真的图像，这引发了对其被用于恶意目的的严重担忧。本文提出采用轻量级的多局部本征维度（multiLID）方法——该方法最初是为检测对抗样本而开发的——来实现对合成图像的自动检测以及相应生成网络的识别。与许多现有检测方法（通常仅适用于生成对抗网络生成的图像）不同，所提方法在多种实际应用场景中均能实现近乎完美的检测效果。在已知及新创建数据集上的广泛实验表明，multiLID在扩散检测与模型识别方面展现出优越性。鉴于近期关于生成图像检测的实证研究往往过度聚焦于"LSUN-Bedroom"数据集，我们进一步建立了一个针对扩散生成图像的综合性基准测试，包括来自多个扩散模型、具有不同图像分辨率的样本，以评估multiLID的性能。实验代码已在https://github.com/deepfake-study/deepfake_multiLID上提供。