Imperial College London

DrSoterisDemetriou

Faculty of EngineeringDepartment of Computing

Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 8237s.demetriou Website CV

 
 
//

Assistant

 

Ms Lucy Atthis +44 (0)20 7594 8259

 
//

Location

 

353ACE ExtensionSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Woszczyk:2021:10.1145/3469261.3469405,
author = {Woszczyk, D and Lee, A and Demetriou, S},
doi = {10.1145/3469261.3469405},
pages = {7--12},
publisher = {ACM},
title = {Open, sesame! Introducing access control to voice services},
url = {http://dx.doi.org/10.1145/3469261.3469405},
year = {2021}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - 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.
AU - Woszczyk,D
AU - Lee,A
AU - Demetriou,S
DO - 10.1145/3469261.3469405
EP - 12
PB - ACM
PY - 2021///
SP - 7
TI - Open, sesame! Introducing access control to voice services
UR - http://dx.doi.org/10.1145/3469261.3469405
UR - http://hdl.handle.net/10044/1/90127
ER -