Guardado en:
Detalles Bibliográficos
Autores principales: Guerra-Balboa, Patricia, Miranda-Pascual, Àlex, Parra-Arnau, Javier, Strufe, Thorsten
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2308.14649
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911842559852544
author Guerra-Balboa, Patricia
Miranda-Pascual, Àlex
Parra-Arnau, Javier
Strufe, Thorsten
author_facet Guerra-Balboa, Patricia
Miranda-Pascual, Àlex
Parra-Arnau, Javier
Strufe, Thorsten
contents The composition theorems of differential privacy (DP) allow data curators to combine different algorithms to obtain a new algorithm that continues to satisfy DP. However, new granularity notions (i.e., neighborhood definitions), data domains, and composition settings have appeared in the literature that the classical composition theorems do not cover. For instance, the original parallel composition theorem does not translate well to general granularity notions. This complicates the opportunity of composing DP mechanisms in new settings and obtaining accurate estimates of the incurred privacy loss after composition. To overcome these limitations, we study the composability of DP in a general framework and for any kind of data domain or neighborhood definition. We give a general composition theorem in both independent and adaptive versions and we provide analogous composition results for approximate, zero-concentrated, and Gaussian DP. Besides, we study the hypothesis needed to obtain the best composition bounds. Our theorems cover both parallel and sequential composition settings. Importantly, they also cover every setting in between, allowing us to compute the final privacy loss of a composition with greatly improved accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14649
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Composition in Differential Privacy for General Granularity Notions (Long Version)
Guerra-Balboa, Patricia
Miranda-Pascual, Àlex
Parra-Arnau, Javier
Strufe, Thorsten
Cryptography and Security
Data Structures and Algorithms
68P27 (Primary)
The composition theorems of differential privacy (DP) allow data curators to combine different algorithms to obtain a new algorithm that continues to satisfy DP. However, new granularity notions (i.e., neighborhood definitions), data domains, and composition settings have appeared in the literature that the classical composition theorems do not cover. For instance, the original parallel composition theorem does not translate well to general granularity notions. This complicates the opportunity of composing DP mechanisms in new settings and obtaining accurate estimates of the incurred privacy loss after composition. To overcome these limitations, we study the composability of DP in a general framework and for any kind of data domain or neighborhood definition. We give a general composition theorem in both independent and adaptive versions and we provide analogous composition results for approximate, zero-concentrated, and Gaussian DP. Besides, we study the hypothesis needed to obtain the best composition bounds. Our theorems cover both parallel and sequential composition settings. Importantly, they also cover every setting in between, allowing us to compute the final privacy loss of a composition with greatly improved accuracy.
title Composition in Differential Privacy for General Granularity Notions (Long Version)
topic Cryptography and Security
Data Structures and Algorithms
68P27 (Primary)
url https://arxiv.org/abs/2308.14649