Deepfake Video Detection via Facial Action Dependencies Estimation

Lingfeng Tan, Yunhong Wang, Junfu Wang, Liang Yang, Xunxun Chen, Yuanfang Guo

Abstract

Deepfake video detection has drawn significant attention from researchers due to the security issues induced by deepfake videos. Unfortunately, most of the existing deepfake detection approaches have not competently modeled the natural structures and movements of human faces. In this paper, we formulate the deepfake video detection problem into a graph classification task, and propose a novel paradigm named Facial Action Dependencies Estimation (FADE) for deepfake video detection. We propose a Multi-Dependency Graph Module (MDGM) to capture abundant dependencies among facial action units, and extracts subtle clues in these dependencies. MDGM can be easily integrated into the existing frame-level detection schemes to provide significant performance gains. Extensive experiments demonstrate the superiority of our method against the state-of-the-art methods.
BibTeX
@inproceedings{tan2023deepfake,
  author = {Lingfeng Tan and Yunhong Wang and Junfu Wang and Liang Yang and Xunxun Chen and Yuanfang Guo},
  title = {{Deepfake Video Detection via Facial Action Dependencies Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2023},
  doi = {10.1609/aaai.v37i4.25658},
}
Figure