Laplace Transform Interpretation of Differential Privacy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910697439363072 |
|---|---|
| author | Chourasia, Rishav Javaid, Uzair Sikdar, Biplap |
| author_facet | Chourasia, Rishav Javaid, Uzair Sikdar, Biplap |
| contents | We introduce a set of useful expressions of Differential Privacy (DP) notions in terms of the Laplace transform of the privacy loss distribution. Its bare form expression appears in several related works on analyzing DP, either as an integral or an expectation. We show that recognizing the expression as a Laplace transform unlocks a new way to reason about DP properties by exploiting the duality between time and frequency domains. Leveraging our interpretation, we connect the $(q, ρ(q))$-Rényi DP curve and the $(ε, δ(ε))$-DP curve as being the Laplace and inverse-Laplace transforms of one another. This connection shows that the Rényi divergence is well-defined for complex orders $q = γ+ i ω$. Using our Laplace transform-based analysis, we also prove an adaptive composition theorem for $(ε, δ)$-DP guarantees that is exactly tight (i.e., matches even in constants) for all values of $ε$. Additionally, we resolve an issue regarding symmetry of $f$-DP on subsampling that prevented equivalence across all functional DP notions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_09142 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Laplace Transform Interpretation of Differential Privacy Chourasia, Rishav Javaid, Uzair Sikdar, Biplap Machine Learning Cryptography and Security We introduce a set of useful expressions of Differential Privacy (DP) notions in terms of the Laplace transform of the privacy loss distribution. Its bare form expression appears in several related works on analyzing DP, either as an integral or an expectation. We show that recognizing the expression as a Laplace transform unlocks a new way to reason about DP properties by exploiting the duality between time and frequency domains. Leveraging our interpretation, we connect the $(q, ρ(q))$-Rényi DP curve and the $(ε, δ(ε))$-DP curve as being the Laplace and inverse-Laplace transforms of one another. This connection shows that the Rényi divergence is well-defined for complex orders $q = γ+ i ω$. Using our Laplace transform-based analysis, we also prove an adaptive composition theorem for $(ε, δ)$-DP guarantees that is exactly tight (i.e., matches even in constants) for all values of $ε$. Additionally, we resolve an issue regarding symmetry of $f$-DP on subsampling that prevented equivalence across all functional DP notions. |
| title | Laplace Transform Interpretation of Differential Privacy |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2411.09142 |