PrivEval: a tool for interactive evaluation of privacy metrics in synthetic data generation
Summary: PrivEval is an interactive tool for evaluating privacy properties of synthetic datasets that implements and validates multiple privacy metrics (per-user and dataset-level) to characterize how DP noise affects the privacy–utility tradeoff. It also checks each metric’s assumptions to surface limitations and improve transparency and usability for practitioners. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Frederik Marinus Trudslev (Aalborg University)
- 2. Matteo Lissandrini (University of Verona)
- 3. Juan Manuel Rodriguez (Aalborg University)
- 4. Martin Bøgsted (Aalborg University; Aalborg University Hospital)
- 5. Daniele Dell’Aglio (Aalborg University)
BibTeX Citation
@article{trudslev_vldb25,
title = {{PrivEval: a tool for interactive evaluation of privacy metrics in synthetic data generation}},
author = {Trudslev, Frederik Marinus and Lissandrini, Matteo and Rodriguez, Juan Manuel and Bøgsted, Martin and Dell’Aglio, Daniele},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {5271--5274},
doi = {10.14778/3750601.3750649},
url = {https://doi.org/10.14778/3750601.3750649},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,129 | Data Synthesis based on Generative Adversarial Networks | 2018 | VLDB | 9.1266572e-05 |
| 3,939 | DPSynthesizer: Differentially Private Data Synthesizer for Privacy Preserving Data Sharing | 2014 | VLDB | 7.008159e-05 |
| 5,008 | Exploring Privacy-Accuracy Tradeoffs using DPComp | 2016 | SIGMOD | 6.4027712e-05 |
| 7,924 | PSynDB: Accurate and Accessible Private Data Generation | 2019 | VLDB | 5.5181056e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,992 | PrivAGM: Secure Construction of Differentially Private Directed Attributed Graph Models on Decentralized Social Graphs | 2025 | VLDB |
| 2 | 3,939 | DPSynthesizer: Differentially Private Data Synthesizer for Privacy Preserving Data Sharing | 2014 | VLDB |
| 3 | 7,909 | Differentially Private Data Generation with Missing Data | 2024 | VLDB |
| 4 | 7,358 | PreFair: Privately Generating Justifiably Fair Synthetic Data | 2023 | VLDB |
| 5 | 11,459 | Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy | 2023 | VLDB |
| 6 | 10,647 | Private Synthetic Data Generation in Bounded Memory | 2025 | PODS |
| 7 | 11,349 | DP-PQD: Privately Detecting Per-Query Gaps In Synthetic Data Generated By Black-Box Mechanisms | 2024 | VLDB |
| 8 | 10,345 | Benchmarking Differentially Private Tabular Data Synthesis: [Experiments & Analysis] | 2026 | SIGMOD |
| 9 | 3,016 | Plausible Deniability for Privacy-Preserving Data Synthesis | 2017 | VLDB |
| 10 | 7,924 | PSynDB: Accurate and Accessible Private Data Generation | 2019 | VLDB |