A survey on differential privacy for unstructured data content
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 …
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
Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …
industries ranging from transportation and healthcare to education and defense …
Vector-indistinguishability: location dependency based privacy protection for successive location data
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 …
has become an increasingly worrying challenge to our community. Existing approaches …
Geo-ellipse-indistinguishability: Community-aware location privacy protection for directional distribution
Directional distribution analysis has long served as a fundamental functionality in
abstracting dispersion and orientation of spatial datasets. Spatial datasets that describe …
abstracting dispersion and orientation of spatial datasets. Spatial datasets that describe …
Introducing the VoicePrivacy initiative
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 …
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 …
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
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 …
user voiceprints that may be abused by malicious adversaries for identity inference or …
Design choices for x-vector based speaker anonymization
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 …
that of a random pseudo-speaker. In this paper, we present a flexible pseudo-speaker …
Differentially private speaker anonymization
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 …
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
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 …
a privacy-utility dilemma when enjoying the utility of voice services. Existing machine-centric …