Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking 2017
DOI: 10.1145/3117811.3117823
|View full text |Cite
|
Sign up to set email alerts
|

Continuous Authentication for Voice Assistants

Abstract: Abstract-Voice has become an increasingly popular User Interaction (UI) channel, mainly contributing to the ongoing trend of wearables, smart vehicles, and home automation systems. Voice assistants such as Siri, Google Now and Cortana, have become our everyday fixtures, especially in scenarios where touch interfaces are inconvenient or even dangerous to use, such as driving or exercising. Nevertheless, the open nature of the voice channel makes voice assistants difficult to secure and exposed to various attack… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
109
0
4

Year Published

2018
2018
2024
2024

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 230 publications
(114 citation statements)
references
References 12 publications
1
109
0
4
Order By: Relevance
“…Thus, ensuring that only authorized sources can trigger voice assistance tools is cumbersome. To provide a further authorization layer, the authors in [103] presented VAuth, a system guaranteeing that the voice assistant executes commands coming only from the voice of the owner. At the triggering of the voice assistant, the system collect accelerometer data from a wearable component mounted at the user's side, and it correlates them with signals coming from the microphone, via the MFCC.…”
Section: B Literature Reviewmentioning
confidence: 99%
“…Thus, ensuring that only authorized sources can trigger voice assistance tools is cumbersome. To provide a further authorization layer, the authors in [103] presented VAuth, a system guaranteeing that the voice assistant executes commands coming only from the voice of the owner. At the triggering of the voice assistant, the system collect accelerometer data from a wearable component mounted at the user's side, and it correlates them with signals coming from the microphone, via the MFCC.…”
Section: B Literature Reviewmentioning
confidence: 99%
“…Phase. Next, we compute the phase changes, which are caused by the time (propagation) delay, t. In particular, we consider t as a sum of every time delay taking place at every propagation medium, e.g., in the air or various body layers, as t = Distance from the transmitter to the user l 2 Distance from the user to the receiver d i1…”
Section: Impact Of Human Body On Wi-fi Signalsmentioning
confidence: 99%
“…Other related studies: VAuth [12] uses a wearable token device to sense the vibrations caused by the speech of the wearer and match the vibration signal with the received voice signal. The matched vibration and voice signals are further used to verify that the voice signal received by a voice assistant is really from the token wearer.…”
Section: Related Workmentioning
confidence: 99%