Privacy-preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification

A. Nelus, J. Ebbers, R. Haeb-Umbach, R. Martin, in: INTERSPEECH 2019, Graz, Austria, 2019.

Download
OA 454.60 KB
Conference Paper | English
Author
; ; ;
Abstract
In this paper we highlight the privacy risks entailed in deep neural network feature extraction for domestic activity monitoring. We employ the baseline system proposed in the Task 5 of the DCASE 2018 challenge and simulate a feature interception attack by an eavesdropper who wants to perform speaker identification. We then propose to reduce the aforementioned privacy risks by introducing a variational information feature extraction scheme that allows for good activity monitoring performance while at the same time minimizing the information of the feature representation, thus restricting speaker identification attempts. We analyze the resulting model’s composite loss function and the budget scaling factor used to control the balance between the performance of the trusted and attacker tasks. It is empirically demonstrated that the proposed method reduces speaker identification privacy risks without significantly deprecating the performance of domestic activity monitoring tasks.
Publishing Year
Proceedings Title
INTERSPEECH 2019, Graz, Austria
LibreCat-ID

Cite this

Nelus A, Ebbers J, Haeb-Umbach R, Martin R. Privacy-preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification. In: INTERSPEECH 2019, Graz, Austria. ; 2019.
Nelus, A., Ebbers, J., Haeb-Umbach, R., & Martin, R. (2019). Privacy-preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification. In INTERSPEECH 2019, Graz, Austria.
@inproceedings{Nelus_Ebbers_Haeb-Umbach_Martin_2019, title={Privacy-preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification}, booktitle={INTERSPEECH 2019, Graz, Austria}, author={Nelus, Alexandru and Ebbers, Janek and Haeb-Umbach, Reinhold and Martin, Rainer}, year={2019} }
Nelus, Alexandru, Janek Ebbers, Reinhold Haeb-Umbach, and Rainer Martin. “Privacy-Preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification.” In INTERSPEECH 2019, Graz, Austria, 2019.
A. Nelus, J. Ebbers, R. Haeb-Umbach, and R. Martin, “Privacy-preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification,” in INTERSPEECH 2019, Graz, Austria, 2019.
Nelus, Alexandru, et al. “Privacy-Preserving Variational Information Feature Extraction for Domestic Activity Monitoring Versus Speaker Identification.” INTERSPEECH 2019, Graz, Austria, 2019.
All files available under the following license(s):
Creative Commons License:
CC0Creative Commons Public Domain Dedication (CC0 1.0)
Main File(s)
Access Level
OA Open Access
Last Uploaded
2020-02-05T10:11:40Z


Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar