Lightweight Protection for Privacy in Offloaded Speech Understanding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Cai, Dongqi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910318407450624
author Cai, Dongqi
author_facet Cai, Dongqi
contents Speech is a common input method for mobile embedded devices, but cloud-based speech recognition systems pose privacy risks. Disentanglement-based encoders, designed to safeguard user privacy by filtering sensitive information from speech signals, unfortunately require substantial memory and computational resources, which limits their use in less powerful devices. To overcome this, we introduce a novel system, XXX, optimized for such devices. XXX is built on the insight that speech understanding primarily relies on understanding the entire utterance's long-term dependencies, while privacy concerns are often linked to short-term details. Therefore, XXX focuses on selectively masking these short-term elements, preserving the quality of long-term speech understanding. The core of XXX is an innovative differential mask generator, grounded in interpretable learning, which fine-tunes the masking process. We tested XXX on the STM32H7 microcontroller, assessing its performance in various potential attack scenarios. The results show that XXX maintains speech understanding accuracy and privacy at levels comparable to existing encoders, but with a significant improvement in efficiency, achieving up to 53.3$\times$ faster processing and a 134.1$\times$ smaller memory footprint.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11983
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lightweight Protection for Privacy in Offloaded Speech Understanding
Cai, Dongqi
Sound
Cryptography and Security
Audio and Speech Processing
Speech is a common input method for mobile embedded devices, but cloud-based speech recognition systems pose privacy risks. Disentanglement-based encoders, designed to safeguard user privacy by filtering sensitive information from speech signals, unfortunately require substantial memory and computational resources, which limits their use in less powerful devices. To overcome this, we introduce a novel system, XXX, optimized for such devices. XXX is built on the insight that speech understanding primarily relies on understanding the entire utterance's long-term dependencies, while privacy concerns are often linked to short-term details. Therefore, XXX focuses on selectively masking these short-term elements, preserving the quality of long-term speech understanding. The core of XXX is an innovative differential mask generator, grounded in interpretable learning, which fine-tunes the masking process. We tested XXX on the STM32H7 microcontroller, assessing its performance in various potential attack scenarios. The results show that XXX maintains speech understanding accuracy and privacy at levels comparable to existing encoders, but with a significant improvement in efficiency, achieving up to 53.3$\times$ faster processing and a 134.1$\times$ smaller memory footprint.
title Lightweight Protection for Privacy in Offloaded Speech Understanding
topic Sound
Cryptography and Security
Audio and Speech Processing
url https://arxiv.org/abs/2401.11983