FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing

Deepfake detectors often struggle to generalize to novel forgery types due to biases learned from limited training data. In this paper, we identify a new type of model bias in the frequency domain, termed spectral bias, where detectors overly rely on specific frequency bands, restricting their ability to generalize across unseen forgeries. To address this, we propose FreqDebias, a frequency debiasing framework that mitigates spectral bias through two complementary strategies. First, we introduce a novel Forgery Mixup (Fo-Mixup) augmentation, which dynamically diversifies frequency characteristics of training samples. Second, we incorporate a dual consistency regularization (CR), which enforces both local consistency using class activation maps (CAMs) and global consistency through a von Mises-Fisher (vMF) distribution on a hyperspherical embedding space. This dual CR mitigates over-reliance on certain frequency components by promoting consistent representation learning under both local and global supervision. Extensive experiments show that FreqDebias significantly enhances cross-domain generalization and outperforms state-of-the-art methods in both cross-domain and in-domain settings.

Key Contributions

• Identifies a new type of model bias called spectral bias, where deepfake detectors over-rely on specific frequency bands, limiting cross-domain generalization.
• Introduces Forgery Mixup (Fo-Mixup), a data augmentation strategy that dynamically modulates amplitude spectra in dominant frequency bands to diversify training samples.
• Proposes dual consistency regularization combining CAM-based local consistency and von Mises-Fisher distribution global consistency on a hyperspherical embedding space to mitigate spectral bias.

🛡️ Threat Analysis

Details

Similar Papers