Understanding the Sparse Vector Technique for Differential Privacy
Summary: Analyzes SVT variants for differential privacy, exposing flaws and misunderstandings across interactive and non-interactive settings. Proposes a tighter SVT with improved utility; in non-interactive DP, EM outperforms SVT, while interactive gains vary. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Min Lyu
- 2. Dong Su
- 3. Ninghui Li
Incoming Citations (Sorted by Pagerank)
Showing 11 of 11 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 136 | Revealing Information while Preserving Privacy | 2003 | PODS | 0.0004241101 |
| 1,446 | PrivBayes: Private Data Release via Bayesian Networks | 2014 | SIGMOD | 0.0001194108 |
| 1,520 | PrivTree: A Differentially Private Algorithm for Hierarchical Decompositions | 2016 | SIGMOD | 0.00011535148 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| Overall Rank | Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,486 | Differential Privacy in Data Publication and Analysis | 2012 | SIGMOD | 5.0445043e-05 |
| 9,512 | Answering Private Linear Queries Adaptively using the Common Mechanism | 2023 | VLDB | 4.3335882e-05 |
| 8,930 | Privacy Preservation by Disassociation | 2012 | VLDB | 4.427232e-05 |
| 10,041 | A General Framework for Per-record Differential Privacy | 2026 | SIGMOD | 4.1945683e-05 |
| 10,992 | Personalized Truncation for Personalized Privacy | 2024 | SIGMOD | 4.1945683e-05 |
| 3,381 | Privacy-preserving Anonymization of Set-valued Data | 2008 | VLDB | 7.1604078e-05 |
| 2,274 | An Adaptive Mechanism for Accurate Query Answering under Differential Privacy | 2012 | VLDB | 9.1297703e-05 |
| 3,097 | Publishing Set-Valued Data via Differential Privacy | 2011 | VLDB | 7.5647028e-05 |
| 9,417 | Free Gap Information from the Differentially Private Sparse Vector and Noisy Max Mechanisms | 2020 | VLDB | 4.3441378e-05 |
| 9,033 | Unleash the Power of Ellipsis: Accuracy-enhanced Sparse Vector Technique with Exponential Noise | 2025 | VLDB | 4.4039656e-05 |