KIT | KIT-Bibliothek | Impressum | Datenschutz

Composition in Differential Privacy for General Granularity Notions

Guerra-Balboa, Patricia ORCID iD icon 1; Miranda-Pascual, Àlex ORCID iD icon 1; Parra-Arnau, Javier; Strufe, Thorsten ORCID iD icon 1
1 Kompetenzzentrum für angewandte Sicherheitstechnologie (KASTEL), Karlsruher Institut für Technologie (KIT)

Abstract (englisch):

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.


Preprint §
DOI: 10.5445/IR/1000165561
Veröffentlicht am 13.12.2023
Zugehörige Institution(en) am KIT Kompetenzzentrum für angewandte Sicherheitstechnologie (KASTEL)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 28.08.2024
Sprache Englisch
Identifikator KITopen-ID: 1000165561
HGF-Programm 46.23.01 (POF IV, LK 01) Methods for Engineering Secure Systems
Erschienen in 2024 IEEE 37th Computer Security Foundations Symposium (CSF), 8th-12th July 2024
Veranstaltung 37th IEEE Computer Security Foundations Symposium (2024), Enschede, Niederlande, 08.07.2024 – 12.07.2024
Projektinformation PROPOLIS (BMBF, 16KIS1393K)
Nachgewiesen in Dimensions
arXiv
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page