FTFDNet: Learning to Detect Talking Face Video Manipulation with Tri-Modality Interaction

TL;DR

This paper introduces FTFDNet, a multi-modal deep learning model that combines visual, audio, and motion features with a novel attention mechanism to improve detection of fake talking face videos, especially those manipulated through lip synchronization.

Contribution

The paper proposes FTFDNet with a cross-modal fusion module and a new audio-visual attention mechanism, enhancing fake video detection by leveraging multi-modal cues and motion analysis.

Findings

Outperforms state-of-the-art methods on FTFDD, DFDC, and DF-TIMIT datasets.

Effectively captures disordered motion cues in fake videos.

Improves detection accuracy by integrating audio, visual, and motion features.

Abstract

DeepFake based digital facial forgery is threatening public media security, especially when lip manipulation has been used in talking face generation, and the difficulty of fake video detection is further improved. By only changing lip shape to match the given speech, the facial features of identity are hard to be discriminated in such fake talking face videos. Together with the lack of attention on audio stream as the prior knowledge, the detection failure of fake talking face videos also becomes inevitable. It's found that the optical flow of the fake talking face video is disordered especially in the lip region while the optical flow of the real video changes regularly, which means the motion feature from optical flow is useful to capture manipulation cues. In this study, a fake talking face detection network (FTFDNet) is proposed by incorporating visual, audio and motion features using an efficient cross-modal fusion (CMF) module. Furthermore, a novel audio-visual attention mechanism (AVAM) is proposed to discover more informative features, which can be seamlessly integrated into any audio-visual CNN architecture by modularization. With the additional AVAM, the proposed FTFDNet is able to achieve a better detection performance than other state-of-the-art DeepFake video detection methods not only on the established fake talking face detection dataset (FTFDD) but also on the DeepFake video detection datasets (DFDC and DF-TIMIT).