Making the Most of Parallel Composition in Differential Privacy
We show that the ‘optimal’ use of the parallel composition theorem corresponds to finding the size of the largest subset of queries that ‘overlap’ on the data domain, a quantity we call the maximum overlap of the queries. It has previously been shown that a certain instance of this problem, formulat...
Enregistré dans:
Auteurs principaux: | Smith Josh, Asghar Hassan Jameel, Gioiosa Gianpaolo, Mrabet Sirine, Gaspers Serge, Tyler Paul |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Sciendo
2022
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/2d316acc6e2445f09a898b07d3ad25d1 |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Differentially private partition selection
par: Desfontaines Damien, et autres
Publié: (2022) -
Privacy-preserving FairSwap: Fairness and privacy interplay
par: Avizheh Sepideh, et autres
Publié: (2022) -
The Effectiveness of Adaptation Methods in Improving User Engagement and Privacy Protection on Social Network Sites
par: Namara Moses, et autres
Publié: (2022) -
Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
par: Jiang Xue, et autres
Publié: (2022) -
Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
par: Cilloni Thomas, et autres
Publié: (2022)