Compressed Deepfake Video Detection Based on 3D Spatiotemporal Trajectories

TL;DR

This paper introduces a novel deepfake detection method based on 3D spatiotemporal trajectories that remains effective on compressed videos, addressing limitations of existing techniques that perform poorly under compression.

Contribution

The paper proposes a robust deepfake detection approach utilizing 3D motion features and phase space analysis, specifically designed to work well on compressed videos and handle challenging scenarios.

Findings

Effective detection on compressed deepfake videos

Robust features verified by facial landmark consistency

Outperforms existing methods on benchmark datasets

Abstract

The misuse of deepfake technology by malicious actors poses a potential threat to nations, societies, and individuals. However, existing methods for detecting deepfakes primarily focus on uncompressed videos, such as noise characteristics, local textures, or frequency statistics. When applied to compressed videos, these methods experience a decrease in detection performance and are less suitable for real-world scenarios. In this paper, we propose a deepfake video detection method based on 3D spatiotemporal trajectories. Specifically, we utilize a robust 3D model to construct spatiotemporal motion features, integrating feature details from both 2D and 3D frames to mitigate the influence of large head rotation angles or insufficient lighting within frames. Furthermore, we separate facial expressions from head movements and design a sequential analysis method based on phase space motion trajectories to explore the feature differences between genuine and fake faces in deepfake videos. We conduct extensive experiments to validate the performance of our proposed method on several compressed deepfake benchmarks. The robustness of the well-designed features is verified by calculating the consistent distribution of facial landmarks before and after video compression.Our method yields satisfactory results and showcases its potential for practical applications.