Saibot: A Differentially Private Data Search Platform
Summary: Saibot privatizes reusable semiring statistics with a Factorized Privacy Mechanism (FPM), enabling scalable DP data-search for ML-centric dataset augmentations without repeated training/evaluation. FPM minimizes sensitivity via unbiased many-to-many join estimators and noise-redistribution, preserving linear-regression utility (50–90% of nonprivate accuracy on 329 datasets) and outperforming TPM/APM/shuffling. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zezhou Huang
- 2. Jiaxiang Liu
- 3. Daniel Gbenga Alabi
- 4. Raul Castro Fernandez
- 5. Eugene Wu
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,077 | The Fast and the Private: Task-based Dataset Search | 2024 | CIDR | 5.2229324e-05 |
| 10,725 | Suna: Scalable Causal Confounder Discovery over Relational Data | 2025 | VLDB | 4.1945683e-05 |
| 10,946 | An LDP Compatible Sketch for Securely Approximating Set Intersection Cardinalities | 2024 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next