A Unified Framework for Quantifying Privacy Risk in Synthetic Data
Bibliographic record
Abstract
Synthetic data is often presented as a method for sharing sensitive information in a privacy-preserving manner by reproducing the global statistical properties of the original data without dis closing sensitive information about any individual. In practice, as with other anonymization methods, synthetic data cannot entirely eliminate privacy risks. These residual privacy risks need instead to be ex-post uncovered and assessed. However, quantifying the actual privacy risks of any synthetic dataset is a hard task, given the multitude of facets of data privacy. We present Anonymeter, a statistical framework to jointly quantify different types of privacy risks in synthetic tabular datasets. We equip this framework with attack-based evaluations for the singling out, linkability, and inference risks, which are the three key indicators of factual anonymization according to data protection regulations, such as the European General Data Protection Regulation (GDPR). To the best of our knowledge, we are the first to introduce a coherent and legally aligned evaluation of these three privacy risks for synthetic data, as well as to design privacy attacks which model directly the singling out and linkability risks. We demonstrate the effectiveness of our methods by conducting an extensive set of experiments that measure the privacy risks of data with deliberately inserted privacy leakages, and of synthetic data generated with and without differential privacy. Our results highlight that the three privacy risks reported by our framework scale linearly with the amount of privacy leakage in the data. Furthermore, we observe that synthetic data exhibits the lowest vulnerability against linkability, indicating one-to-one relationships between real and synthetic data records are not preserved. Finally, with a quantitative comparison we demonstrate that Anonymeter outperforms existing synthetic data privacy evaluation frameworks both in terms of detecting privacy leaks, as well as computation speed. To contribute to a privacy-conscious usage of synthetic data, we publish Anonymeter as an open-source library (https://github.com/statice/anonymeter).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.029 | 0.112 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.006 | 0.009 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".