Saved in:
Bibliographic Details
Main Authors: He, Peisong, Zhu, Leyao, Li, Jiaxing, Wang, Shiqi, Li, Haoliang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.04133
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911869691756544
author He, Peisong
Zhu, Leyao
Li, Jiaxing
Wang, Shiqi
Li, Haoliang
author_facet He, Peisong
Zhu, Leyao
Li, Jiaxing
Wang, Shiqi
Li, Haoliang
contents The generative model has made significant advancements in the creation of realistic videos, which causes security issues. However, this emerging risk has not been adequately addressed due to the absence of a benchmark dataset for AI-generated videos. In this paper, we first construct a video dataset using advanced diffusion-based video generation algorithms with various semantic contents. Besides, typical video lossy operations over network transmission are adopted to generate degraded samples. Then, by analyzing local and global temporal defects of current AI-generated videos, a novel detection framework by adaptively learning local motion information and global appearance variation is constructed to expose fake videos. Finally, experiments are conducted to evaluate the generalization and robustness of different spatial and temporal domain detection methods, where the results can serve as the baseline and demonstrate the research challenge for future studies.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04133
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exposing AI-generated Videos: A Benchmark Dataset and a Local-and-Global Temporal Defect Based Detection Method
He, Peisong
Zhu, Leyao
Li, Jiaxing
Wang, Shiqi
Li, Haoliang
Computer Vision and Pattern Recognition
The generative model has made significant advancements in the creation of realistic videos, which causes security issues. However, this emerging risk has not been adequately addressed due to the absence of a benchmark dataset for AI-generated videos. In this paper, we first construct a video dataset using advanced diffusion-based video generation algorithms with various semantic contents. Besides, typical video lossy operations over network transmission are adopted to generate degraded samples. Then, by analyzing local and global temporal defects of current AI-generated videos, a novel detection framework by adaptively learning local motion information and global appearance variation is constructed to expose fake videos. Finally, experiments are conducted to evaluate the generalization and robustness of different spatial and temporal domain detection methods, where the results can serve as the baseline and demonstrate the research challenge for future studies.
title Exposing AI-generated Videos: A Benchmark Dataset and a Local-and-Global Temporal Defect Based Detection Method
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.04133