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

Miao, Yuantian, Minhui, Xue, 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, 2021 (1). pp. 209-228.

[img]
Preview
PDF (Published Version) - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (5MB) | Preview
View at Publisher Website: https://doi.org/10.2478/popets-2021-0012
 
84


Abstract

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.

Item ID: 64660
Item Type: Article (Research - C1)
ISSN: 2299-0984
Keywords: membership inference attack, ASR, machine learning
Related URLs:
Funders: Australian Research Council (ARC), Australian Government, Government of Western Australia
Projects and Grants: ARC grant no. LP170100924
Date Deposited: 27 Oct 2020 21:32
FoR Codes: 46 INFORMATION AND COMPUTING SCIENCES > 4604 Cybersecurity and privacy > 460402 Data and information privacy @ 100%
SEO Codes: 89 INFORMATION AND COMMUNICATION SERVICES > 8902 Computer Software and Services > 890299 Computer Software and Services not elsewhere classified @ 100%
Downloads: Total: 84
Last 12 Months: 27
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page