Timezone: »

 
Poster
Capacity Bounded Differential Privacy
Kamalika Chaudhuri · Jacob Imola · Ashwin Machanavajjhala

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #87
in Applications -- Privacy, Anonymity, and Security »

Differential privacy, a notion of algorithmic stability, is a gold standard for measuring the additional risk an algorithm's output poses to the privacy of a single record in the dataset. Differential privacy is defined as the distance between the output distribution of an algorithm on neighboring datasets that differ in one entry. In this work, we present a novel relaxation of differential privacy, capacity bounded differential privacy, where the adversary that distinguishes output distributions is assumed to be capacity-bounded -- i.e. bounded not in computational power, but in terms of the function class from which their attack algorithm is drawn. We model adversaries in terms of restricted f-divergences between probability distributions, and study properties of the definition and algorithms that satisfy them.

Keywords: Learning Theory · Privacy, Anonymity, and Security · Applications · Theory
[ Paper]  [ Poster] 

Author Information

Kamalika Chaudhuri (UCSD)
Jacob Imola (UCSD)
Ashwin Machanavajjhala (Duke)

More from the Same Authors