Openly accessible

The audio auditor: user-level membership inference in Internet of Things voice services

Miao, Yuantian, Xue, Minhui, Chen, Chao, Pan, Lei, Zhang, Jun, Zhao, Benjamin Zi Hao, Kaafar, Dali and Xiang, Yang 2021, The audio auditor: user-level membership inference in Internet of Things voice services, Proceedings on privacy enhancing technologies, vol. 2021, no. 1, pp. 209-228, doi: 10.2478/popets-2021-0012.

Attached Files
Name Description MIMEType Size Downloads

Title The audio auditor: user-level membership inference in Internet of Things voice services
Author(s) Miao, Yuantian
Xue, Minhui
Chen, Chao
Pan, LeiORCID iD for Pan, Lei orcid.org/0000-0002-4691-8330
Zhang, Jun
Zhao, Benjamin Zi Hao
Kaafar, Dali
Xiang, Yang
Journal name Proceedings on privacy enhancing technologies
Volume number 2021
Issue number 1
Start page 209
End page 228
Total pages 20
Publisher De Gruyter Open
Place of publication Warsaw, Poland
Publication date 2021-01
ISSN 2299-0984
Keyword(s) Membership Inference Attack
ASR
Machine Learning
Summary With the rapid development of deep learning techniques, the popularity of voice services implemented on various Internet of Things (IoT) devices is ever increasing. In this paper, we examine user-level membership inference in the problem space of voice services, by designing an audio auditor to verify whether a specific user had unwillingly contributed audio used to train an automatic speech recognition (ASR) model under strict black-box access. With user representation of the input audio data and their corresponding translated text, our trained auditor is effective in user-level audit. We also observe that the auditor trained on specific data can be generalized well regardless of the ASR model architecture. We validate the auditor on ASR models trained with LSTM, RNNs, and GRU algorithms on two state-of-the-art pipelines, the hybrid ASR system and the end-to-end ASR system. Finally, we conduct a real-world trial of our auditor on iPhone Siri, achieving an overall accuracy exceeding 80%. We hope the methodology developed in this paper and findings can inform privacy advocates to overhaul IoT privacy.
Language eng
DOI 10.2478/popets-2021-0012
Indigenous content off
HERDC Research category C1 Refereed article in a scholarly journal
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30147977

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 25 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Thu, 11 Feb 2021, 09:47:55 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.