2008 49th Annual IEEE Symposium on Foundations of Computer Science (2008)

Oct. 25, 2008 to Oct. 28, 2008

ISSN: 0272-5428

ISBN: 978-0-7695-3436-7

pp: 531-540

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/FOCS.2008.27

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.

INDEX TERMS

Database Privacy, Learning Theory, PAC Learning

CITATION

S. Raskhodnikova, A. Smith, H. K. Lee, K. Nissim and S. P. Kasiviswanathan, "What Can We Learn Privately?,"

*2008 49th Annual IEEE Symposium on Foundations of Computer Science(FOCS)*, vol. 00, no. , pp. 531-540, 2008.

doi:10.1109/FOCS.2008.27