What can we learn privately?

Shiva Prasad Kasiviswanathan, Hornin K. Lee, Kobbi Nissim, Sofya Raskhodnikova, Adam Smith

Research output: Chapter in Book/Report/Conference proceedingConference contribution

157 Scopus citations

Abstract

Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept classes can be learned privately, namely, by an algorithm whose output does not depend too heavily on any one input or specific training example ? More precisely, we investigate learning algorithms that satisfy differential privacy, a notion that provides strong confidentiality guarantees in the contexts where aggregate information is released about a database containing sensitive information about individuals. We present several basic results that demonstrate gene ral feasibility of private learning and relate several models previously studied separately in the contexts of privacy and standard learning.

Original languageEnglish (US)
Title of host publicationProceedings of the 49th Annual IEEE Symposium on Foundations of Computer Science, FOCS 2008
PublisherIEEE Computer Society
Pages531-540
Number of pages10
ISBN (Print)9780769534367
DOIs
StatePublished - 2008
Event49th Annual IEEE Symposium on Foundations of Computer Science, FOCS 2008 - Philadelphia, PA, United States
Duration: Oct 25 2008Oct 28 2008

Publication series

NameProceedings - Annual IEEE Symposium on Foundations of Computer Science, FOCS
ISSN (Print)0272-5428

Other

Other49th Annual IEEE Symposium on Foundations of Computer Science, FOCS 2008
Country/TerritoryUnited States
CityPhiladelphia, PA
Period10/25/0810/28/08

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'What can we learn privately?'. Together they form a unique fingerprint.

Cite this