S
Shiva Prasad Kasiviswanathan
Researcher at Amazon.com
Publications - 100
Citations - 5413
Shiva Prasad Kasiviswanathan is an academic researcher from Amazon.com. The author has contributed to research in topics: Differential privacy & Computer science. The author has an hindex of 29, co-authored 91 publications receiving 4421 citations. Previous affiliations of Shiva Prasad Kasiviswanathan include Pennsylvania State University & Los Alamos National Laboratory.
Papers
More filters
Journal ArticleDOI
What Can We Learn Privately
TL;DR: This work investigates 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.
Posted Content
What Can We Learn Privately
TL;DR: In this paper, it was shown that a concept class is learnable by a local algorithm if and only if it is learnedable in the statistical query (SQ) model.
Proceedings ArticleDOI
Composition attacks and auxiliary information in data privacy
TL;DR: This paper investigates composition attacks, in which an adversary uses independent anonymized releases to breach privacy, and provides a precise formulation of this property, and proves that an important class of relaxations of differential privacy also satisfy the property.
Book ChapterDOI
Analyzing graphs with node differential privacy
TL;DR: A generic, efficient reduction is derived that allows us to apply any differentially private algorithm for bounded-degree graphs to an arbitrary graph, based on analyzing the smooth sensitivity of the 'naive' truncation that simply discards nodes of high degree.
Posted Content
Composition Attacks and Auxiliary Information in Data Privacy
TL;DR: In this paper, the authors investigate composition attacks, in which an adversary uses independent anonymized releases to breach privacy, and demonstrate that even a simple instance of a composition attack can breach privacy in practice, for a large class of currently proposed techniques.