Home // UBICOMM 2018, The Twelfth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies // View article

Dummy-Based Anonymization for Voice-Controlled IoT Devices

Authors:
Katrin Winkler
Erik Buchmann

Keywords: User Privacy; Internet of Things; Voice Control.

Abstract:
Voice assistants like Amazon Alexa, Google Assistant or Siri are becoming increasingly popular. Such assistants allow for complex interactions with smart Internet-of-Things (IoT) devices that do not have a traditional user interface, such as monitor and keyboard. However, while voice assistants foster the proliferation of numerous convenient services from smart homes to connected cars, they are problematic from the perspective of user privacy. In many cases, IoT devices are permanently listening for keywords in sensitive areas such as living rooms or bed rooms. Once such a word is recognized, voice samples are sent to the voice-assistant provider into the cloud for further analyses. We explore how the users of IoT devices can anonymize the voice recordings sent to the voice-assistant provider. To this end, we identify categories of information sent to the provider, we describe an anonymization approach based on dummy voice commands, and we describe a prototypical anonymization device based on a Raspberry PI. Our device confirms that it is possible to anonymize some information sent to Alexa with limited inconveniences for the user.

Pages: 1 to 8

Copyright: Copyright (c) IARIA, 2018

Publication date: November 18, 2018

Published in: conference

ISSN: 2308-4278

ISBN: 978-1-61208-676-7

Location: Athens, Greece

Dates: from November 18, 2018 to November 22, 2018