Open, sesame! Introducing access control to voice services
File(s)
Accepted version
Author(s)
Woszczyk, Dominika
Lee, Alvin
Demetriou, Soteris
Type
Conference Paper
Abstract
Personal voice assistants (VAs) are shown to be vulnerable against record–and–replay, and other acoustic attacks which allow an adversary to gain unauthorized control of connected devices within a smart home. Existing defenses either lack detection and management capabilities or are too coarse-grained to enable flexible policies on par with other computing interfaces. In this work, we present Sesame, a lightweight framework for edge devices which is the first to enable fine-grained access control of smart-home voice commands. Sesame combines three components: Automatic SpeechRecognition, Natural Language Understanding (NLU) and a Policymodule. We implemented Sesame on Android devices and demonstrate that our system can enforce security policies for both Alexa and Google Home in real-time (362ms end-to-end inference time), with a lightweight (<25MB) NLU model which exhibits minimal accuracy loss compared to its non-compact equivalent.
Date Issued
2021-06-24
Date Acceptance
2021-05-26
Citation
MAISP'21: Proceedings of the 1st Workshop on Security and Privacy for Mobile AI, 2021, pp.7-12
ISBN
9781450386012
Publisher
ACM
Start Page
7
End Page
12
Journal / Book Title
MAISP'21: Proceedings of the 1st Workshop on Security and Privacy for Mobile AI
Copyright Statement
© 2021 ACM. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in MAISP'21: Proceedings of the 1st Workshop on Security and Privacy for Mobile AI, Jun 2021, https://dl.acm.org/doi/10.1145/3469261.3469405
Source
1st Workshop on Security and Privacy for Mobile AI (MAISP)
Publication Status
Published
Start Date
2021-06-25
Coverage Spatial
Virtual