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...
Guardado en:
Autores principales: | Smith Josh, Asghar Hassan Jameel, Gioiosa Gianpaolo, Mrabet Sirine, Gaspers Serge, Tyler Paul |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Sciendo
2022
|
Materias: | |
Acceso en línea: | https://doaj.org/article/2d316acc6e2445f09a898b07d3ad25d1 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Differentially private partition selection
por: Desfontaines Damien, et al.
Publicado: (2022) -
Privacy-preserving FairSwap: Fairness and privacy interplay
por: Avizheh Sepideh, et al.
Publicado: (2022) -
The Effectiveness of Adaptation Methods in Improving User Engagement and Privacy Protection on Social Network Sites
por: Namara Moses, et al.
Publicado: (2022) -
Privacy-Preserving High-dimensional Data Collection with Federated Generative Autoencoder
por: Jiang Xue, et al.
Publicado: (2022) -
Ulixes: Facial Recognition Privacy with Adversarial Machine Learning
por: Cilloni Thomas, et al.
Publicado: (2022)