Normalization-consistent data curation for generalizable deepfake detection

Shijie Hou

doi:10.1016/j.neucom.2025.131838

Normalization-consistent data curation for generalizable deepfake detection

2025-10-16

0

PRE

AI

DOI：10.1016/j.neucom.2025.131838

Original

Original request for help

Save

Abstract

En 中文

Deepfake has recently garnered considerable attention due to its potential threat. Recent detectors often struggle to generalize due to sensitivity to dataset-specific biases. We identify a key factor: their performance varies significantly with different normalization parameters, indicating reliance on preprocessing artifacts rather than authentic manipulation traces. To address this, we propose Normalization-Consistent Data Curation (NormCura), which selects training samples based on their prediction stability across normalization variations. NormCura first evaluates sample consistency under multiple normalization conditions, then trains only on stable samples. This filters out normalization-sensitive artifacts while retaining robust forensic patterns. Extensive cross-dataset evaluations on nine deepfake datasets demonstrate that this approach significantly improves generalization performance, including emerging diffusion-based synthetic faces, confirming that normalization consistency is an effective proxy for learning generalizable deepfake detection features.

Normalization-consistent data curation for generalizable deepfake detection

Abstract

Journal

Organization