A survey on differential privacy for unstructured data content

Y Zhao, J Chen - ACM Computing Surveys (CSUR), 2022 - dl.acm.org
Huge amounts of unstructured data including image, video, audio, and text are ubiquitously
generated and shared, and it is a challenge to protect sensitive personal information in …

[PDF][PDF] A review of speech-centric trustworthy machine learning: Privacy, safety, and fairness

T Feng, R Hebbar, N Mehlman, X Shi… - … on Signal and …, 2023 - nowpublishers.com
Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …

Vector-indistinguishability: location dependency based privacy protection for successive location data

Y Zhao, J Chen - IEEE Transactions on Computers, 2023 - ieeexplore.ieee.org
With the wide use of GPS enabled devices and Location-Based Services, location privacy
has become an increasingly worrying challenge to our community. Existing approaches …

Geo-ellipse-indistinguishability: Community-aware location privacy protection for directional distribution

Y Zhao, D Yuan, JT Du, J Chen - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Directional distribution analysis has long served as a fundamental functionality in
abstracting dispersion and orientation of spatial datasets. Spatial datasets that describe …

Introducing the VoicePrivacy initiative

N Tomashenko, BML Srivastava, X Wang… - arXiv preprint arXiv …, 2020 - arxiv.org
The VoicePrivacy initiative aims to promote the development of privacy preservation tools for
speech technology by gathering a new community to define the tasks of interest and the …

[HTML][HTML] X-vector anonymization using autoencoders and adversarial training for preserving speech privacy

JM Perero-Codosero, FM Espinoza-Cuadros… - Computer speech & …, 2022 - Elsevier
The rapid increase in web services and mobile apps, which collect personal data from users,
has also increased the risk that their privacy may be severely compromised. In particular, the …

{V-Cloak}: Intelligibility-, Naturalness-& {Timbre-Preserving}{Real-Time} Voice Anonymization

J Deng, F Teng, Y Chen, X Chen, Z Wang… - 32nd USENIX Security …, 2023 - usenix.org
Voice data generated on instant messaging or social media applications contains unique
user voiceprints that may be abused by malicious adversaries for identity inference or …

Design choices for x-vector based speaker anonymization

BML Srivastava, N Tomashenko, X Wang… - arXiv preprint arXiv …, 2020 - arxiv.org
The recently proposed x-vector based anonymization scheme converts any input voice into
that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker …

Differentially private speaker anonymization

AS Shamsabadi, BML Srivastava, A Bellet… - arXiv preprint arXiv …, 2022 - arxiv.org
Sharing real-world speech utterances is key to the training and deployment of voice-based
services. However, it also raises privacy risks as speech contains a wealth of personal data …

VoiceCloak: Adversarial Example Enabled Voice De-Identification with Balanced Privacy and Utility

M Chen, L Lu, J Wang, J Yu, Y Chen, Z Wang… - Proceedings of the …, 2023 - dl.acm.org
Faced with the threat of identity leakage during voice data publishing, users are engaged in
a privacy-utility dilemma when enjoying the utility of voice services. Existing machine-centric …