Reduced relative errors for short sequence counting with differential privacy

  • Sergiu Costea
  • , Gabriel Ghinita
  • , Rvzvan Rughinis
  • , Nicolae Tapus

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Current concerns about data privacy have lead to increased focus on data anonymization methods. Differential privacy is a new mechanism that offers formal guarantees about anonymization strength. The main challenge when using differential privacy consists in the difficulty in designing correct algorithms when operating on complex data types. One such data type is sequential data, which is used to model many actions like location or browsing history. We propose a new differential privacy algorithm for short sequence counting called Recursive Budget Allocation (RBA). We show that RBA leads to lower relative errors than current state of the art techniques. In addition, it can also be used to improve relative errors for generic differential privacy algorithms which operate on data trees.

Original languageEnglish
Title of host publicationProceedings - 2015 20th International Conference on Control Systems and Computer Science, CSCS 2015
EditorsIoan Dumitrache, Adina Magda Florea, Florin Pop, Alexandru Dumitrascu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages475-482
Number of pages8
ISBN (Electronic)9781479917792
DOIs
Publication statusPublished - 27 Jul 2015
Externally publishedYes
Event20th International Conference on Control Systems and Computer Science, CSCS 2015 - Bucharest, Romania
Duration: 27 May 201529 May 2015

Publication series

NameProceedings - 2015 20th International Conference on Control Systems and Computer Science, CSCS 2015

Conference

Conference20th International Conference on Control Systems and Computer Science, CSCS 2015
Country/TerritoryRomania
CityBucharest
Period27/05/1529/05/15

Keywords

  • Differential privacy
  • Optimization
  • Privacy
  • Sequence counting

Fingerprint

Dive into the research topics of 'Reduced relative errors for short sequence counting with differential privacy'. Together they form a unique fingerprint.

Cite this