Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning

TL;DR

This paper introduces EMSFD, a novel approach that models class evidence with Dirichlet distributions and uses active learning to improve synthetic face detection's reliability, accuracy, and generalizability.

Contribution

EMSFD explicitly incorporates uncertainty modeling and active learning to enhance synthetic face detection, reducing labeling costs and improving performance over existing methods.

Findings

Achieves a 15% accuracy increase over SOTA baselines.

Enhances interpretability of synthetic face detection.

Improves detection reliability and generalizability.

Abstract

With the rapid development of deep generative models, forged facial images are massively exploited for illegal activities. Although existing synthetic face detection methods have achieved significant progress, they suffer from the inherent limitation of overconfidence due to their reliance on the Softmax activation function. Thus, these methods often lead to unreliable predictions when encountering unknown Out-of-Distribution (OOD) images, and cannot ascertain the model's uncertainty in its prediction. Meanwhile, most existing methods require massive high-quality annotated data, which greatly limits their practicability across diverse scenarios. To address these limitations, we propose EMSFD (Evidence-based decision Modeling for Synthetic Face Detection with uncertainty-driven active learning), an approach designed to enhance detection reliability and generalizability. Specifically, EMSFD models class evidence using the Dirichlet distribution and explicitly incorporates model uncertainty into the prediction process. Furthermore, during training, the estimated uncertainty is exploited to prioritize more informative samples from the unlabeled pool for annotation, thereby reducing labeling cost and improving model generalization. Extensive experimental evaluations demonstrate that our method enhances the interpretability of synthetic face detection. Meanwhile, our method yields a 15\% increase in accuracy compared to existing state-of-the-art (SOTA) baselines, which demonstrates the superior detection performance and generalizability of our approach. Our code is available at: https://github.com/hzx111621/EMSFD.