An Overview of Face Deep Forgery

Li Xinwei, Guo Jinlin, Chen Junnan
{"title":"An Overview of Face Deep Forgery","authors":"Li Xinwei, Guo Jinlin, Chen Junnan","doi":"10.1109/ICCEA53728.2021.00078","DOIUrl":null,"url":null,"abstract":"With the rise of deep learning and the improvement of computer computing power, many interesting topics have emerged in the field of DeepFake in recent years. Deep forgery includes, but is not limited to, the forgery of human faces, but also the forgery of scenes. Among them, deep forgery of human face has received greater attention due to its importance and sensitivity. At present, various cutting-edge deep forgery methods can easily forge fake faces that are difficult for ordinary people to distinguish, which has already posed a threat to information security and social trust. This paper focuses on face deep forgery, will introduce different types of face deep forgery and its technologies. And we found that deep forgery’ s real-time and robustness are crutial drawbakcs. Finally, the future development trend of deep forgery of human face are proposed.","PeriodicalId":325790,"journal":{"name":"2021 International Conference on Computer Engineering and Application (ICCEA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Computer Engineering and Application (ICCEA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCEA53728.2021.00078","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

With the rise of deep learning and the improvement of computer computing power, many interesting topics have emerged in the field of DeepFake in recent years. Deep forgery includes, but is not limited to, the forgery of human faces, but also the forgery of scenes. Among them, deep forgery of human face has received greater attention due to its importance and sensitivity. At present, various cutting-edge deep forgery methods can easily forge fake faces that are difficult for ordinary people to distinguish, which has already posed a threat to information security and social trust. This paper focuses on face deep forgery, will introduce different types of face deep forgery and its technologies. And we found that deep forgery’ s real-time and robustness are crutial drawbakcs. Finally, the future development trend of deep forgery of human face are proposed.
人脸深度伪造概述
随着深度学习的兴起和计算机计算能力的提高,近年来DeepFake领域出现了许多有趣的话题。深度伪造包括但不限于对人脸的伪造,还包括对场景的伪造。其中,人脸深度伪造因其重要性和敏感性而受到越来越多的关注。目前,各种尖端的深度伪造方法可以轻易伪造普通人难以分辨的假脸,已经对信息安全和社会信任构成威胁。本文以人脸深度伪造为重点,介绍了不同类型的人脸深度伪造及其技术。我们发现深度伪造的实时性和鲁棒性是关键的缺点。最后,对人脸深度伪造的未来发展趋势进行了展望。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信