TALL: Thumbnail Layout for Deepfake Video Detection

The growing threats of deepfakes to society and cybersecurity have raised enormous public concerns, and increasing efforts have been devoted to this critical topic of deepfake video detection. Existing video methods achieve good performance but are computationally intensive. This paper introduces a...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Xu, Yuting, Liang, Jian, Jia, Gengyun, Yang, Ziming, Zhang, Yanhao, He, Ran
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 18.02.2024
Subjects
Cybersecurity
Datasets
Deception
Layouts
Thumbnail icons
Online AccessGet full text

Cover

More Information
Summary:The growing threats of deepfakes to society and cybersecurity have raised enormous public concerns, and increasing efforts have been devoted to this critical topic of deepfake video detection. Existing video methods achieve good performance but are computationally intensive. This paper introduces a simple yet effective strategy named Thumbnail Layout (TALL), which transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies. Specifically, consecutive frames are masked in a fixed position in each frame to improve generalization, then resized to sub-images and rearranged into a pre-defined layout as the thumbnail. TALL is model-agnostic and extremely simple by only modifying a few lines of code. Inspired by the success of vision transformers, we incorporate TALL into Swin Transformer, forming an efficient and effective method TALL-Swin. Extensive experiments on intra-dataset and cross-dataset validate the validity and superiority of TALL and SOTA TALL-Swin. TALL-Swin achieves 90.79\(\%\) AUC on the challenging cross-dataset task, FaceForensics++ \(\to\) Celeb-DF. The code is available at https://github.com/rainy-xu/TALL4Deepfake.
ISSN:2331-8422