聚焦LRP:面部变形攻击检测的可解释AI

Clemens Seibold, A. Hilsmann, P. Eisert
{"title":"聚焦LRP:面部变形攻击检测的可解释AI","authors":"Clemens Seibold, A. Hilsmann, P. Eisert","doi":"10.1109/WACVW52041.2021.00014","DOIUrl":null,"url":null,"abstract":"The task of detecting morphed face images has become highly relevant in recent years to ensure the security of automatic verification systems based on facial images, e.g. automated border control gates. Detection methods based on Deep Neural Networks (DNN) have been shown to be very suitable to this end. However, they do not provide transparency in the decision making and it is not clear how they distinguish between genuine and morphed face images. This is particularly relevant for systems intended to assist a human operator, who should be able to understand the reasoning. In this paper, we tackle this problem and present Focused Layer-wise Relevance Propagation (FLRP). This framework explains to a human inspector on a precise pixel level, which image regions are used by a Deep Neural Network to distinguish between a genuine and a morphed face image. Additionally, we propose another framework to objectively analyze the quality of our method and compare FLRP to other DNN interpretability methods. This evaluation framework is based on removing detected artifacts and analyzing the influence of these changes on the decision of the DNN. Especially, if the DNN is uncertain in its decision or even incorrect, FLRP performs much better in highlighting visible artifacts compared to other methods.","PeriodicalId":313062,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Focused LRP: Explainable AI for Face Morphing Attack Detection\",\"authors\":\"Clemens Seibold, A. Hilsmann, P. Eisert\",\"doi\":\"10.1109/WACVW52041.2021.00014\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The task of detecting morphed face images has become highly relevant in recent years to ensure the security of automatic verification systems based on facial images, e.g. automated border control gates. Detection methods based on Deep Neural Networks (DNN) have been shown to be very suitable to this end. However, they do not provide transparency in the decision making and it is not clear how they distinguish between genuine and morphed face images. This is particularly relevant for systems intended to assist a human operator, who should be able to understand the reasoning. In this paper, we tackle this problem and present Focused Layer-wise Relevance Propagation (FLRP). This framework explains to a human inspector on a precise pixel level, which image regions are used by a Deep Neural Network to distinguish between a genuine and a morphed face image. Additionally, we propose another framework to objectively analyze the quality of our method and compare FLRP to other DNN interpretability methods. This evaluation framework is based on removing detected artifacts and analyzing the influence of these changes on the decision of the DNN. Especially, if the DNN is uncertain in its decision or even incorrect, FLRP performs much better in highlighting visible artifacts compared to other methods.\",\"PeriodicalId\":313062,\"journal\":{\"name\":\"2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)\",\"volume\":\"48 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WACVW52041.2021.00014\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WACVW52041.2021.00014","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10

摘要

近年来,检测变形人脸图像已成为确保基于人脸图像的自动验证系统(如自动边境控制门)安全性的重要任务。基于深度神经网络(DNN)的检测方法已被证明非常适合这一目的。然而,它们在决策过程中没有提供透明度,也不清楚它们如何区分真实的和变形的人脸图像。这对于旨在帮助人类操作员的系统尤其重要,因为操作员应该能够理解推理。在本文中,我们解决了这个问题,并提出了聚焦分层相关传播(FLRP)。这个框架在精确的像素级别上向人类检查员解释,深度神经网络使用哪些图像区域来区分真实的人脸图像和变形的人脸图像。此外,我们提出了另一个框架来客观地分析我们的方法的质量,并将FLRP与其他DNN可解释性方法进行比较。该评估框架基于去除检测到的伪影并分析这些变化对深度神经网络决策的影响。特别是,如果DNN的决定是不确定的,甚至是不正确的,FLRP在突出显示可见伪像方面比其他方法表现得更好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Focused LRP: Explainable AI for Face Morphing Attack Detection
The task of detecting morphed face images has become highly relevant in recent years to ensure the security of automatic verification systems based on facial images, e.g. automated border control gates. Detection methods based on Deep Neural Networks (DNN) have been shown to be very suitable to this end. However, they do not provide transparency in the decision making and it is not clear how they distinguish between genuine and morphed face images. This is particularly relevant for systems intended to assist a human operator, who should be able to understand the reasoning. In this paper, we tackle this problem and present Focused Layer-wise Relevance Propagation (FLRP). This framework explains to a human inspector on a precise pixel level, which image regions are used by a Deep Neural Network to distinguish between a genuine and a morphed face image. Additionally, we propose another framework to objectively analyze the quality of our method and compare FLRP to other DNN interpretability methods. This evaluation framework is based on removing detected artifacts and analyzing the influence of these changes on the decision of the DNN. Especially, if the DNN is uncertain in its decision or even incorrect, FLRP performs much better in highlighting visible artifacts compared to other methods.
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:481959085
Book学术官方微信