Composition Theorems for f-Differential Privacy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914220033966080 |
|---|---|
| author | Fernandes, Natasha McIver, Annabelle Sadeghi, Parastoo |
| author_facet | Fernandes, Natasha McIver, Annabelle Sadeghi, Parastoo |
| contents | "f differential privacy" (fDP) is a recent definition for privacy privacy which can offer improved predictions of "privacy loss". It has been used to analyse specific privacy mechanisms, such as the popular Gaussian mechanism. In this paper we show how fDP's foundation in statistical hypothesis testing implies equivalence to the channel model of Quantitative Information Flow. We demonstrate this equivalence by a Galois connection between two partially ordered sets. This equivalence enables novel general composition theorems for fDP, supporting improved analysis for complex privacy designs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21358 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Composition Theorems for f-Differential Privacy Fernandes, Natasha McIver, Annabelle Sadeghi, Parastoo Cryptography and Security Information Theory "f differential privacy" (fDP) is a recent definition for privacy privacy which can offer improved predictions of "privacy loss". It has been used to analyse specific privacy mechanisms, such as the popular Gaussian mechanism. In this paper we show how fDP's foundation in statistical hypothesis testing implies equivalence to the channel model of Quantitative Information Flow. We demonstrate this equivalence by a Galois connection between two partially ordered sets. This equivalence enables novel general composition theorems for fDP, supporting improved analysis for complex privacy designs. |
| title | Composition Theorems for f-Differential Privacy |
| topic | Cryptography and Security Information Theory |
| url | https://arxiv.org/abs/2512.21358 |