Skip to yearly menu bar Skip to main content


Poster

Exploiting Style Latent Flows for Generalizing Deepfake Video Detection

Jongwook Choi · Taehoon Kim · Yonghyun Jeong · Seungryul Baek · Jongwon Choi

Arch 4A-E Poster #95
[ ] [ Paper PDF ]
[ Poster
Wed 19 Jun 10:30 a.m. PDT — noon PDT

Abstract:

This paper presents a new approach for the detection of fake videos, based on the analysis of style latent vectors and their abnormal behavior in temporal changes in the generated videos. We discovered that the generated facial videos suffer from the temporal distinctiveness in the temporal changes of style latent vectors, which are inevitable during the generation of temporally stable videos with various facial expressions and geometric transformations. Our framework utilizes the Style GRU module, trained by contrastive learning, to represent the dynamic properties of style latent vectors. Additionally, we introduce a style attention module that integrates Style GRU-generated features with content-based features, enabling the detection of visual and temporal artifacts. We demonstrate our approach across various benchmark scenarios in deepfake detection, showing its superiority in cross-dataset and cross-manipulation scenarios. Through further analysis, we also validate the importance of using temporal changes of style latent vectors to improve the generality of deepfake video detection.

Chat is not available.