人脸识别安全吗?

Sanjay Saha, T. Sim
{"title":"人脸识别安全吗?","authors":"Sanjay Saha, T. Sim","doi":"10.1109/IJCB48548.2020.9304864","DOIUrl":null,"url":null,"abstract":"Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition Systems are vulnerable to attacks and can lead to erroneous identification of faces. Interestingly, most of these attacks are white-box, or they are manipulating facial images in ways that are not physically realizable. In this paper, we propose an attack scheme where the attacker can generate realistic synthesized face images with subtle perturbations and physically realize that onto his face to attack black-box face recognition systems. Comprehensive experiments and analyses show that subtle perturbations realized on attackers face can create successful attacks on state-of-the-art face recognition systems in black-box settings. Our study exposes the underlying vulnerability posed by the Face Recognition Systems against realizable black-box attacks.","PeriodicalId":417270,"journal":{"name":"2020 IEEE International Joint Conference on Biometrics (IJCB)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Is Face Recognition Safe from Realizable Attacks?\",\"authors\":\"Sanjay Saha, T. Sim\",\"doi\":\"10.1109/IJCB48548.2020.9304864\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition Systems are vulnerable to attacks and can lead to erroneous identification of faces. Interestingly, most of these attacks are white-box, or they are manipulating facial images in ways that are not physically realizable. In this paper, we propose an attack scheme where the attacker can generate realistic synthesized face images with subtle perturbations and physically realize that onto his face to attack black-box face recognition systems. Comprehensive experiments and analyses show that subtle perturbations realized on attackers face can create successful attacks on state-of-the-art face recognition systems in black-box settings. Our study exposes the underlying vulnerability posed by the Face Recognition Systems against realizable black-box attacks.\",\"PeriodicalId\":417270,\"journal\":{\"name\":\"2020 IEEE International Joint Conference on Biometrics (IJCB)\",\"volume\":\"49 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-09-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE International Joint Conference on Biometrics (IJCB)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IJCB48548.2020.9304864\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Joint Conference on Biometrics (IJCB)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IJCB48548.2020.9304864","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

人脸识别是一种流行的生物识别认证形式,由于其广泛使用,攻击也变得越来越普遍。最近的研究表明,人脸识别系统容易受到攻击,并可能导致错误的人脸识别。有趣的是,这些攻击大多是白盒攻击,或者他们以物理上无法实现的方式操纵面部图像。在本文中,我们提出了一种攻击方案,攻击者可以生成具有细微扰动的逼真合成人脸图像,并将其物理实现到他的脸上,以攻击黑盒人脸识别系统。综合实验和分析表明,在攻击者面部上实现的细微扰动可以在黑盒设置中对最先进的面部识别系统进行成功的攻击。我们的研究揭示了人脸识别系统对可实现的黑盒攻击所构成的潜在漏洞。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Is Face Recognition Safe from Realizable Attacks?
Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition Systems are vulnerable to attacks and can lead to erroneous identification of faces. Interestingly, most of these attacks are white-box, or they are manipulating facial images in ways that are not physically realizable. In this paper, we propose an attack scheme where the attacker can generate realistic synthesized face images with subtle perturbations and physically realize that onto his face to attack black-box face recognition systems. Comprehensive experiments and analyses show that subtle perturbations realized on attackers face can create successful attacks on state-of-the-art face recognition systems in black-box settings. Our study exposes the underlying vulnerability posed by the Face Recognition Systems against realizable black-box attacks.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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:604180095
Book学术官方微信