Differential Privacy for Text Analytics via Natural Text Sanitization

Xiang Yue, Minxin Du, Tianhao Wang, Yaliang Li, Huan Sun, Sherman S.M. Chow

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

31 Citations (Scopus)

Abstract

Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization mechanisms still provide low utility, as cursed by the high-dimensional text representation. The companion issue of utilizing sanitized texts for downstream analytics is also under-explored. This paper takes a direct approach to text sanitization. Our insight is to consider both sensitivity and similarity via our new local DP notion. The sanitized texts also contribute to our sanitization-aware pretraining and fine-tuning, enabling privacy-preserving natural language processing over the BERT language model with promising utility. Surprisingly, the high utility does not boost up the success rate of inference attacks.

Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationACL-IJCNLP 2021
EditorsChengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
PublisherAssociation for Computational Linguistics (ACL)
Pages3853-3866
Number of pages14
ISBN (Electronic)9781954085541
Publication statusPublished - Aug 2021
EventFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021 - Virtual, Online
Duration: 1 Aug 20216 Aug 2021

Publication series

NameFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021

Conference

ConferenceFindings of the Association for Computational Linguistics: ACL-IJCNLP 2021
CityVirtual, Online
Period1/08/216/08/21

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Differential Privacy for Text Analytics via Natural Text Sanitization'. Together they form a unique fingerprint.

Cite this