Metric geometry of the privacy-utility tradeoff
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914778749861888 |
|---|---|
| author | Boedihardjo, March Strohmer, Thomas Vershynin, Roman |
| author_facet | Boedihardjo, March Strohmer, Thomas Vershynin, Roman |
| contents | Synthetic data are an attractive concept to enable privacy in data sharing. A fundamental question is how similar the privacy-preserving synthetic data are compared to the true data. Using metric privacy, an effective generalization of differential privacy beyond the discrete setting, we raise the problem of characterizing the optimal privacy-accuracy tradeoff by the metric geometry of the underlying space. We provide a partial solution to this problem in terms of the "entropic scale", a quantity that captures the multiscale geometry of a metric space via the behavior of its packing numbers. We illustrate the applicability of our privacy-accuracy tradeoff framework via a diverse set of examples of metric spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_00329 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Metric geometry of the privacy-utility tradeoff Boedihardjo, March Strohmer, Thomas Vershynin, Roman Cryptography and Security Data Structures and Algorithms Probability Synthetic data are an attractive concept to enable privacy in data sharing. A fundamental question is how similar the privacy-preserving synthetic data are compared to the true data. Using metric privacy, an effective generalization of differential privacy beyond the discrete setting, we raise the problem of characterizing the optimal privacy-accuracy tradeoff by the metric geometry of the underlying space. We provide a partial solution to this problem in terms of the "entropic scale", a quantity that captures the multiscale geometry of a metric space via the behavior of its packing numbers. We illustrate the applicability of our privacy-accuracy tradeoff framework via a diverse set of examples of metric spaces. |
| title | Metric geometry of the privacy-utility tradeoff |
| topic | Cryptography and Security Data Structures and Algorithms Probability |
| url | https://arxiv.org/abs/2405.00329 |