all InfoSec news
Membership Inference Attacks Against Self-supervised Speech Models. (arXiv:2111.05113v3 [cs.CR] UPDATED)
Aug. 5, 2022, 1:20 a.m. | Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee
cs.CR updates on arXiv.org arxiv.org
Recently, adapting the idea of self-supervised learning (SSL) on continuous
speech has started gaining attention. SSL models pre-trained on a huge amount
of unlabeled audio can generate general-purpose representations that benefit a
wide variety of speech processing tasks. Despite their ubiquitous deployment,
however, the potential privacy risks of these models have not been well
investigated. In this paper, we present the first privacy analysis on several
SSL speech models using Membership Inference Attacks (MIA) under black-box
access. The experiment results …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Security Audit and Compliance Technical Analyst
@ Accenture Federal Services | Washington, DC
ICS Cyber Threat Intelligence Analyst
@ STEMBoard | Arlington, Virginia, United States
Cyber Operations Analyst
@ Peraton | Arlington, VA, United States
Cybersecurity – Information System Security Officer (ISSO)
@ Boeing | USA - Annapolis Junction, MD
Network Security Engineer I - Weekday Afternoons
@ Deepwatch | Remote