Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu, Zhenxing Qian, Xinpeng Zhang, Zaiwang Gu• 2026

Related benchmarks

TaskDatasetResultRank
Synthetic Face DetectionStyleGAN2 OOD
Accuracy93.5
7
Synthetic Face DetectionVQGAN OOD
Accuracy86.1
7
Synthetic Face DetectionIDDPM OOD
Accuracy99.6
7
Synthetic Face DetectionLDM OOD
Accuracy99.3
7
Synthetic Face DetectionOverall (Average)
Accuracy96.4
7
Synthetic Face DetectionREAL ID
Accuracy99.8
7
Synthetic Face DetectionADM ID
Accuracy (%)99
7
Synthetic Face DetectionStyleGAN ID
Accuracy97.4
7
Synthetic Face DetectionOOD (Out-of-Distribution)
ECE0.0516
3
Synthetic Image DetectionFLUX.2 (test)
Accuracy64.9
3
Showing 10 of 10 rows

Other info

Follow for update