Detecting AutoEncoder is Enough to Catch LDM Generated Images

TL;DR

A novel method for detecting images generated by Latent Diffusion Models by identifying artifacts introduced by their autoencoders by training a detector to distinguish between real images and those reconstructed by the LDM autoencoder.

Abstract

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.

Figures (5)

• Figure 1: Popularity graph of image generation-related search queries on Google
• Figure 2: LDM Architecture Schematic
• Figure 3: The approach for detecting generated images
• Figure 4: Visualization results of JPEG (left) and reconstructed (right) images
• Figure 5: Visualization results of EfficientNet-V2 B0 (left), ConvNext Large (middle) and EVA-02 ViT L/14 (right)