Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing
Summary: Introduces reconstruction advantage, a unified disclosure-risk metric for DP that subsumes membership, attribute inference, and reconstruction. Derives tight noise-to-risk bounds and optimal attacks, enabling principled noise calibration and systematic DP auditing beyond ReRo. (summarized by gpt-5.4-mini on May 27 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
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 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 83 | Privacy Integrated Queries: An Extensible Platform for Privacy-Preserving Data Analysis | 2009 | SIGMOD | 0.00053933811 |
| 5,497 | Real-World Trajectory Sharing with Local Differential Privacy | 2021 | VLDB | 5.4752255e-05 |
| 7,797 | Quantifying identifiability to choose and audit epsilon in differentially private deep learning | 2021 | VLDB | 4.6482625e-05 |
| 8,280 | Synthetic Tabular Data: Methods, Attacks and Defenses | 2025 | VLDB | 4.5435639e-05 |
| 8,283 | Measuring Re-identification Risk | 2023 | SIGMOD | 4.5435639e-05 |
| 8,312 | Privacy Preserving Serial Data Publishing By Role Composition | 2008 | VLDB | 4.5435639e-05 |
| 11,227 | On the Risks of Collecting Multidimensional Data Under Local Differential Privacy | 2023 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next