Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes

TL;DR

This paper introduces a novel method for detecting lip-sync DeepFake videos by exploiting inconsistencies between lip movements and audio, achieving over 95% accuracy and creating a new dataset for further research.

Contribution

The paper presents the first dedicated approach to lip-forgery detection that leverages biological links between lips and head regions, along with a new high-quality dataset for the field.

Findings

Achieves over 95.3% accuracy in spotting lip-sync DeepFakes.

Demonstrates robustness against diverse input transformations.

Performs well in real-world scenarios like WeChat video calls.

Abstract

In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humanity. DeepFake can be bifurcated into entertainment applications like face swapping and illicit uses such as lip-syncing fraud. However, lip-forgery videos, which neither change identity nor have discernible visual artifacts, present a formidable challenge to existing DeepFake detection methods. Our preliminary experiments have shown that the effectiveness of the existing methods often drastically decrease or even fail when tackling lip-syncing videos. In this paper, for the first time, we propose a novel approach dedicated to lip-forgery identification that exploits the inconsistency between lip movements and audio signals. We also mimic human natural cognition by capturing subtle biological links between lips and head regions to boost accuracy. To better illustrate the effectiveness and advances of our proposed method, we create a high-quality LipSync dataset, AVLips, by employing the state-of-the-art lip generators. We hope this high-quality and diverse dataset could be well served the further research on this challenging and interesting field. Experimental results show that our approach gives an average accuracy of more than 95.3% in spotting lip-syncing videos, significantly outperforming the baselines. Extensive experiments demonstrate the capability to tackle deepfakes and the robustness in surviving diverse input transformations. Our method achieves an accuracy of up to 90.2% in real-world scenarios (e.g., WeChat video call) and shows its powerful capabilities in real scenario deployment. To facilitate the progress of this research community, we release all resources at https://github.com/AaronComo/LipFD.