VLA

Author:

Shen Meng1,Liao Zelin1,Zhu Liehuang1,Xu Ke2,Du Xiaojiang3

Affiliation:

1. Beijing Institute of Technology, Beijing, China

2. Tsinghua University & BNRist, Beijing, China

3. Temple University, Philadelphia, PA, USA

Abstract

Adversarial example attacks have become a growing menace to neural network-based face recognition systems. Generated by composing facial images with pixel-level perturbations, adversarial examples change key features of inputs and thereby lead to misclassification of neural networks. However, the perturbation loss caused by complex physical environments sometimes prevents existing attack methods from taking effect. In this paper, we focus on designing new attacks that are effective and inconspicuous in the physical world. Motivated by the differences in image-forming principles between cameras and human eyes, we propose VLA, a novel attack against black-box face recognition systems using visible light. In VLA, visible light-based adversarial perturbations are crafted and projected on human faces, which allows an adversary to conduct targeted or un-targeted attacks. VLA decomposes adversarial perturbations into a perturbation frame and a concealing frame, where the former adds modifications on human facial images while the latter makes these modifications inconspicuous to human eyes. We conduct extensive experiments to demonstrate the effectiveness, inconspicuousness, and robustness of the adversarial examples crafted by VLA in physical scenarios.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture,Human-Computer Interaction

Reference48 articles.

1. 2018. Arrivals SmartGate. https://www.homeaffairs.gov.au/trav/ente/goin/arrival/smartgateor-epassport. (Accessed on 07/05/2018). 2018. Arrivals SmartGate. https://www.homeaffairs.gov.au/trav/ente/goin/arrival/smartgateor-epassport. (Accessed on 07/05/2018).

2. 2018. davidsandberg/facenet: Face recognition using Tensorflow. https://github.com/davidsandberg/facenet. (Accessed on 11/05/2018). 2018. davidsandberg/facenet: Face recognition using Tensorflow. https://github.com/davidsandberg/facenet. (Accessed on 11/05/2018).

3. 2018. dlib C++ Library. http://dlib.net/. (Accessed on 11/05/2018). 2018. dlib C++ Library. http://dlib.net/. (Accessed on 11/05/2018).

4. 2018. LFW: Results. http://vis-www.cs.umass.edu/lfw/results.html. (Accessed on 11/05/2018). 2018. LFW: Results. http://vis-www.cs.umass.edu/lfw/results.html. (Accessed on 11/05/2018).

5. 2019. Facebook's New Facial Recognition Photo Tagging. https://vtldesign.com/digital-marketing/social-media/nh-facebook-marketing/how-to-disable-facebook-facial-recognition-photo-tagging-nhmarketing/. (Accessed on 04/22/2019). 2019. Facebook's New Facial Recognition Photo Tagging. https://vtldesign.com/digital-marketing/social-media/nh-facebook-marketing/how-to-disable-facebook-facial-recognition-photo-tagging-nhmarketing/. (Accessed on 04/22/2019).

Cited by 22 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

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