Privacy amplification by subsampling: Tight analyses via couplings and divergences
Differential privacy comes equipped with multiple analytical tools for the design of private
data analyses. One important tool is the so-called" privacy amplification by subsampling"
principle, which ensures that a differentially private mechanism run on a random subsample
of a population provides higher privacy guarantees than when run on the entire population.
Several instances of this principle have been studied for different random subsampling
methods, each with an ad-hoc analysis. In this paper we present a general method that …
data analyses. One important tool is the so-called" privacy amplification by subsampling"
principle, which ensures that a differentially private mechanism run on a random subsample
of a population provides higher privacy guarantees than when run on the entire population.
Several instances of this principle have been studied for different random subsampling
methods, each with an ad-hoc analysis. In this paper we present a general method that …
[HTML][HTML] Privacy amplification by subsampling: Tight analyses via couplings and divergences
B de Balle Pigem, G Barthe, M Gaboardi - 2018 - amazon.science
Differential privacy comes equipped with multiple analytical tools for the design of private
data analyses. One important tool is the so-called “privacy amplification by subsampling”
principle, which ensures that a differentially private mechanism run on a random subsample
of a population provides higher privacy guarantees than when run on the entire population.
Several instances of this principle have been studied for different random subsampling
methods, each with an ad-hoc analysis. In this paper we present a general method that …
data analyses. One important tool is the so-called “privacy amplification by subsampling”
principle, which ensures that a differentially private mechanism run on a random subsample
of a population provides higher privacy guarantees than when run on the entire population.
Several instances of this principle have been studied for different random subsampling
methods, each with an ad-hoc analysis. In this paper we present a general method that …
Showing the best results for this search. See all results