Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914887975829504 |
|---|---|
| author | Ganev, Georgi |
| author_facet | Ganev, Georgi |
| contents | In this paper, we argue that similarity-based privacy metrics cannot ensure regulatory compliance of synthetic data. Our analysis and counter-examples show that they do not protect against singling out and linkability and, among other fundamental issues, completely ignore the motivated intruder test. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16929 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance Ganev, Georgi Cryptography and Security Artificial Intelligence Computers and Society In this paper, we argue that similarity-based privacy metrics cannot ensure regulatory compliance of synthetic data. Our analysis and counter-examples show that they do not protect against singling out and linkability and, among other fundamental issues, completely ignore the motivated intruder test. |
| title | Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance |
| topic | Cryptography and Security Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2407.16929 |