English

Towards Generalizable Deepfake Detection via Forgery-aware Audio-Visual Adaptation: A Variational Bayesian Approach

Multimedia 2025-11-25 v1 Computer Vision and Pattern Recognition

Abstract

The widespread application of AIGC contents has brought not only unprecedented opportunities, but also potential security concerns, e.g., audio-visual deepfakes. Therefore, it is of great importance to develop an effective and generalizable method for multi-modal deepfake detection. Typically, the audio-visual correlation learning could expose subtle cross-modal inconsistencies, e.g., audio-visual misalignment, which serve as crucial clues in deepfake detection. In this paper, we reformulate the correlation learning with variational Bayesian estimation, where audio-visual correlation is approximated as a Gaussian distributed latent variable, and thus develop a novel framework for deepfake detection, i.e., Forgery-aware Audio-Visual Adaptation with Variational Bayes (FoVB). Specifically, given the prior knowledge of pre-trained backbones, we adopt two core designs to estimate audio-visual correlations effectively. First, we exploit various difference convolutions and a high-pass filter to discern local and global forgery traces from both modalities. Second, with the extracted forgery-aware features, we estimate the latent Gaussian variable of audio-visual correlation via variational Bayes. Then, we factorize the variable into modality-specific and correlation-specific ones with orthogonality constraint, allowing them to better learn intra-modal and cross-modal forgery traces with less entanglement. Extensive experiments demonstrate that our FoVB outperforms other state-of-the-art methods in various benchmarks.

Keywords

Cite

@article{arxiv.2511.19080,
  title  = {Towards Generalizable Deepfake Detection via Forgery-aware Audio-Visual Adaptation: A Variational Bayesian Approach},
  author = {Fan Nie and Jiangqun Ni and Jian Zhang and Bin Zhang and Weizhe Zhang and Bin Li},
  journal= {arXiv preprint arXiv:2511.19080},
  year   = {2025}
}

Comments

TIFS AQE

R2 v1 2026-07-01T07:52:05.806Z