Vision Transformer-Based Video Hashing Retrieval for Tracing the Source of Fake Videos

Author:

Pei Pengfei12ORCID,Zhao Xianfeng12ORCID,Li Jinchuan12ORCID,Cao Yun12ORCID,Lai Xuyuan12ORCID

Affiliation:

1. State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100083, China

2. School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100083, China

Abstract

With the increasing negative impact of fake videos on individuals and society, it is crucial to detect different types of forgeries. Existing forgery detection methods often output a probability value, which lacks interpretability and reliability. In this paper, we propose a source-tracing-based solution to find the original real video of a fake video, which can provide more reliable results in practical situations. However, directly applying retrieval methods to traceability tasks is infeasible since traceability tasks require finding the unique source video from a large number of real videos, while retrieval methods are typically used to find similar videos. In addition, training an effective hashing center to distinguish similar real videos is challenging. To address the above issues, we introduce a novel loss function, hash triplet loss, to capture fine-grained features with subtle differences. Extensive experiments show that our method outperforms state-of-the-art methods on multiple datasets of object removal (video inpainting), object addition (video splicing), and object swapping (face swapping), demonstrating excellent robustness and cross-dataset performance. The effectiveness of the hash triplet loss for nondifferentiable optimization problems is validated through experiments in similar video scenes.

Funder

National Basic Research Program of China

Publisher

Hindawi Limited

Subject

Computer Networks and Communications,Information Systems

Reference76 articles.

1. ADD: frequency attention and multi-view based knowledge distillation to detect low-quality compressed deepfake images;L. M. Binh,2022

2. Robust image forgery detection against transmission over online social networks;H. Wu;IEEE Transactions on Information Forensics and Security,2022

3. ISTVT: Interpretable Spatial-Temporal Video Transformer for Deepfake Detection

4. Towards an end-to-end framework for flow-guided video inpainting;Z. Li

5. Dlformer: discrete latent transformer for video inpainting;J. Ren

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3