Continuous Authentication for Voice Assistants

被引:174
作者
Feng, Huan [1 ]
Fawaz, Kassem [1 ]
Shin, Kang G. [1 ]
机构
[1] Univ Michigan, Ann Arbor, MI 48109 USA
来源
PROCEEDINGS OF THE 23RD ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING (MOBICOM '17) | 2017年
关键词
D O I
10.1145/3117811.3117823
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Voice has become an increasingly popular User Interaction (UI) channel, mainly contributing to the current trend of wearables, smart vehicles, and home automation systems. Voice assistants such as Alexa, Siri, and Google Now, have become our everyday fixtures, especially when/where touch interfaces are inconvenient or even dangerous to use, such as driving or exercising. The open nature of the voice channel makes voice assistants difficult to secure, and hence exposed to various threats as demonstrated by security researchers. To defend against these threats, we present VAuth, the first system that provides continuous authentication for voice assistants. VAuth is designed to fit in widely-adopted wearable devices, such as eyeglasses, earphones/buds and necklaces, where it collects the body-surface vibrations of the user and matches it with the speech signal received by the voice assistant's microphone. VAuth guarantees the voice assistant to execute only the commands that originate from the voice of the owner. We have evaluated VAuth with 18 users and 30 voice commands and find it to achieve 97% detection accuracy and less than 0.1% false positive rate, regardless of VAuth's position on the body and the user's language, accent or mobility. VAuth successfully thwarts various practical attacks, such as replay attacks, mangled voice attacks, or impersonation attacks. It also incurs low energy and latency overheads and is compatible with most voice assistants.
引用
收藏
页码:343 / 355
页数:13
相关论文
共 40 条
[1]  
Ackerman Eugene, 1962, MRLTDR6236 PENNS U U
[2]  
[Anonymous], 2012, P 7 USENIX C HOT TOP
[3]  
[Anonymous], 1993, IFA P, DOI DOI 10.1371/JOURNAL.PONE.0069107
[4]  
[Anonymous], 2016, BBC NEWS
[5]  
[Anonymous], 2012, Proceedings of the fifth ACM conference on Security and Privacy in Wireless and Mobile Networks
[6]  
[Anonymous], 1990, SUPPORT VECTOR LEARN
[7]  
[Anonymous], 2010, J COMPUT, DOI DOI 10.5815/IJIGSP.2016.09.03
[8]  
[Anonymous], 2015, 9 USENIX WORKSHOP OF
[9]  
Aviv AJ, 2012, 28TH ANNUAL COMPUTER SECURITY APPLICATIONS CONFERENCE (ACSAC 2012), P41
[10]  
Baloul M., 2012, Biometrics Special Interest Group (BIOSIG), 2012 BIOSIG-Proceedings of the International Conference of the, P1