Gaussian differential privacy

In the past decade, differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in anal...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of the Royal Statistical Society. Series B, Statistical methodology Jg. 84; H. 1; S. 3 - 37
Hauptverfasser:	Dong, Jinshuo, Roth, Aaron, Su, Weijie J.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Oxford Oxford University Press 01.02.2022
Schlagworte:	Algorithms Amplification Blackwell theorem Central limit theorem Composition Data analysis Descent differential privacy Families & family life GDP Gross Domestic Product Hypotheses Hypothesis testing methodology normal distribution primal‐dual perspective Privacy privacy amplification private stochastic gradient descent Property Regression analysis Relaxation Statistical methods Statistics subsampling Theorems trade‐off function
ISSN:	1369-7412, 1467-9868
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!