In this section
@article{Aloufi:2023:10.1145/3570161,
author = {Aloufi, R and Haddadi, H and Boyle, D},
doi = {10.1145/3570161},
journal = {ACM Transactions on Privacy and Security},
pages = {1--27},
title = {Paralinguistic privacy protection at the edge},
url = {http://dx.doi.org/10.1145/3570161},
volume = {26},
year = {2023}
}
TY - JOUR
AB - Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further processing and subsequent actions. Our voices and raw audio signals collected through these devices contain a host of sensitive paralinguistic information that is transmitted to service providers regardless of deliberate or false triggers. As our emotional patterns and sensitive attributes like our identity, gender, and well-being are easily inferred using deep acoustic models, we encounter a new generation of privacy risks by using these services. One approach to mitigate the risk of paralinguistic-based privacy breaches is to exploit a combination of cloud-based processing with privacy-preserving, on-device paralinguistic information learning and filtering before transmitting voice data.In this article we introduce EDGY, a configurable, lightweight, disentangled representation learning framework that transforms and filters high-dimensional voice data to identify and contain sensitive attributes at the edge prior to offloading to the cloud. We evaluate EDGY’s on-device performance and explore optimization techniques, including model quantization and knowledge distillation, to enable private, accurate, and efficient representation learning on resource-constrained devices. Our results show that EDGY runs in tens of milliseconds with 0.2% relative improvement in “zero-shot” ABX score or minimal performance penalties of approximately 5.95% word error rate (WER) in learning linguistic representations from raw voice signals, using a CPU and a single-core ARM processor without specialized hardware.
AU - Aloufi,R
AU - Haddadi,H
AU - Boyle,D
DO - 10.1145/3570161
EP - 27
PY - 2023///
SN - 2471-2566
SP - 1
TI - Paralinguistic privacy protection at the edge
T2 - ACM Transactions on Privacy and Security
UR - http://dx.doi.org/10.1145/3570161
UR - http://hdl.handle.net/10044/1/105218
VL - 26
ER -
Dyson School of Design Engineering
Imperial College London
25 Exhibition Road
South Kensington
London
SW7 2DB
design.engineering@imperial.ac.uk
Tel: +44 (0) 20 7594 8888