PIVOT

Privacy-preserving outsourcing of text data for word embedding against frequency analysis attack

Yanying Li, Wendy Hui Wang, Boxiang Dong

Research output: Contribution to journalConference articleResearchpeer-review

Abstract

In this paper, we design PIVOT, a new privacy-preserving method that supports outsourcing of text data for word embedding. PIVOT includes a 1-to-many mapping function for text documents that can defend against the frequency analysis attack with provable guarantee, while preserving the word context during transformation.

Original languageEnglish
Pages (from-to)77-79
Number of pages3
JournalCEUR Workshop Proceedings
Volume2335
StatePublished - 1 Jan 2019
Event2019 PAL: Privacy-Enhancing Artificial Intelligence and Language Technologies, PAL 2019 - Palo Alto, United States
Duration: 25 Mar 201927 Mar 2019

Fingerprint

Outsourcing

Cite this

@article{3b71af4a0a9f430389f5ee9ab5ff1f49,
title = "PIVOT: Privacy-preserving outsourcing of text data for word embedding against frequency analysis attack",
abstract = "In this paper, we design PIVOT, a new privacy-preserving method that supports outsourcing of text data for word embedding. PIVOT includes a 1-to-many mapping function for text documents that can defend against the frequency analysis attack with provable guarantee, while preserving the word context during transformation.",
author = "Yanying Li and Wang, {Wendy Hui} and Boxiang Dong",
year = "2019",
month = "1",
day = "1",
language = "English",
volume = "2335",
pages = "77--79",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",

}

PIVOT : Privacy-preserving outsourcing of text data for word embedding against frequency analysis attack. / Li, Yanying; Wang, Wendy Hui; Dong, Boxiang.

In: CEUR Workshop Proceedings, Vol. 2335, 01.01.2019, p. 77-79.

Research output: Contribution to journalConference articleResearchpeer-review

TY - JOUR

T1 - PIVOT

T2 - Privacy-preserving outsourcing of text data for word embedding against frequency analysis attack

AU - Li, Yanying

AU - Wang, Wendy Hui

AU - Dong, Boxiang

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, we design PIVOT, a new privacy-preserving method that supports outsourcing of text data for word embedding. PIVOT includes a 1-to-many mapping function for text documents that can defend against the frequency analysis attack with provable guarantee, while preserving the word context during transformation.

AB - In this paper, we design PIVOT, a new privacy-preserving method that supports outsourcing of text data for word embedding. PIVOT includes a 1-to-many mapping function for text documents that can defend against the frequency analysis attack with provable guarantee, while preserving the word context during transformation.

UR - http://www.scopus.com/inward/record.url?scp=85063283153&partnerID=8YFLogxK

M3 - Conference article

VL - 2335

SP - 77

EP - 79

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -