Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection

TL;DR

This paper introduces DEUA, a novel method for detecting diffusion-generated images by estimating epistemic uncertainty and employing asymmetric learning, achieving state-of-the-art results on large benchmarks.

Contribution

The paper proposes a new framework that distinguishes epistemic from aleatoric uncertainty and uses asymmetric loss to improve detection of diffusion-generated images.

Findings

DEUA achieves superior detection accuracy on benchmark datasets.

Estimating epistemic uncertainty enhances the generalizability of the detector.

Asymmetric training improves the classifier's robustness against diverse data.

Abstract

The rapid progress of diffusion models highlights the growing need for detecting generated images. Previous research demonstrates that incorporating diffusion-based measurements, such as reconstruction error, can enhance the generalizability of detectors. However, ignoring the differing impacts of aleatoric and epistemic uncertainty on reconstruction error can undermine detection performance. Aleatoric uncertainty, arising from inherent data noise, creates ambiguity that impedes accurate detection of generated images. As it reflects random variations within the data (e.g., noise in natural textures), it does not help distinguish generated images. In contrast, epistemic uncertainty, which represents the model's lack of knowledge about unfamiliar patterns, supports detection. In this paper, we propose a novel framework, Diffusion Epistemic Uncertainty with Asymmetric Learning~(DEUA), for detecting diffusion-generated images. We introduce Diffusion Epistemic Uncertainty~(DEU) estimation via the Laplace approximation to assess the proximity of data to the manifold of diffusion-generated samples. Additionally, an asymmetric loss function is introduced to train a balanced classifier with larger margins, further enhancing generalizability. Extensive experiments on large-scale benchmarks validate the state-of-the-art performance of our method.