Composable and versatile privacy via truncated CDP

STOC '18: Symposium on Theory of Computing Los Angeles CA USA June, 2018, pp. 74-86, 2018.

Cited by: 38|Bibtex|Views64|DOI:https://doi.org/10.1145/3188745.3188946
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|dl.acm.org

Abstract:

We propose truncated concentrated differential privacy (tCDP), a refinement of differential privacy and of concentrated differential privacy. This new definition provides robust and efficient composition guarantees, supports powerful algorithmic techniques such as privacy amplification via sub-sampling, and enables more accurate statistic...More

Code:

Data:

Your rating :
0

 

Tags
Comments