HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images

TL;DR

HFI is a training-free, efficient framework that detects images generated by latent diffusion models and implicitly watermarks them by measuring aliasing in reconstructed images.

Contribution

It introduces HFI, a novel method that measures aliasing to improve detection of LDM-generated images without training data, outperforming existing methods.

Findings

HFI outperforms existing training-free detection methods.

HFI effectively detects images from various generative models.

HFI can implicitly watermark images generated by LDMs.

Abstract

Dramatic advances in the quality of the latent diffusion models (LDMs) also led to the malicious use of AI-generated images. While current AI-generated image detection methods assume the availability of real/AI-generated images for training, this is practically limited given the vast expressibility of LDMs. This motivates the training-free detection setup where no related data are available in advance. The existing LDM-generated image detection method assumes that images generated by LDM are easier to reconstruct using an autoencoder than real images. However, we observe that this reconstruction distance is overfitted to background information, leading the current method to underperform in detecting images with simple backgrounds. To address this, we propose a novel method called HFI. Specifically, by viewing the autoencoder of LDM as a downsampling-upsampling kernel, HFI measures the extent of aliasing, a distortion of high-frequency information that appears in the reconstructed image. HFI is training-free, efficient, and consistently outperforms other training-free methods in detecting challenging images generated by various generative models. We also show that HFI can successfully detect the images generated from the specified LDM as a means of implicit watermarking. HFI outperforms the best baseline method while achieving magnitudes of