Privacy Amplification for the Gaussian Mechanism via Bounded Support
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910359030333440 |
|---|---|
| author | Hu, Shengyuan Mahloujifar, Saeed Smith, Virginia Chaudhuri, Kamalika Guo, Chuan |
| author_facet | Hu, Shengyuan Mahloujifar, Saeed Smith, Virginia Chaudhuri, Kamalika Guo, Chuan |
| contents | Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. These guarantees can be desirable compared to vanilla DP in real world settings as they tightly upper-bound the privacy leakage for a $\textit{specific}$ individual in an $\textit{actual}$ dataset, rather than considering worst-case datasets. While these frameworks are beginning to gain popularity, to date, there is a lack of private mechanisms that can fully leverage advantages of data-dependent accounting. To bridge this gap, we propose simple modifications of the Gaussian mechanism with bounded support, showing that they amplify privacy guarantees under data-dependent accounting. Experiments on model training with DP-SGD show that using bounded support Gaussian mechanisms can provide a reduction of the pDP bound $ε$ by as much as 30% without negative effects on model utility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05598 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Privacy Amplification for the Gaussian Mechanism via Bounded Support Hu, Shengyuan Mahloujifar, Saeed Smith, Virginia Chaudhuri, Kamalika Guo, Chuan Cryptography and Security Machine Learning Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. These guarantees can be desirable compared to vanilla DP in real world settings as they tightly upper-bound the privacy leakage for a $\textit{specific}$ individual in an $\textit{actual}$ dataset, rather than considering worst-case datasets. While these frameworks are beginning to gain popularity, to date, there is a lack of private mechanisms that can fully leverage advantages of data-dependent accounting. To bridge this gap, we propose simple modifications of the Gaussian mechanism with bounded support, showing that they amplify privacy guarantees under data-dependent accounting. Experiments on model training with DP-SGD show that using bounded support Gaussian mechanisms can provide a reduction of the pDP bound $ε$ by as much as 30% without negative effects on model utility. |
| title | Privacy Amplification for the Gaussian Mechanism via Bounded Support |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2403.05598 |