Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure
Summary: Novel geometric PLRV analysis for spherically symmetric noise via a radius–direction product measure, yielding closed-form DP moment bounds. Under the same (eps,delta)[0m-DP, it beats Gaussian noise in high dimensions and improves output/objective/gradient perturbation for ERM. (summarized by gpt-5-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Shuainan Liu (Texas Tech University)
- 2. Tianxi Ji (Texas Tech University)
- 3. Zhongshuo Fang (Texas Tech University)
- 4. Lu Wei (Texas Tech University)
- 5. Pan Li (Hangzhou Dianzi University)
BibTeX Citation
@inproceedings{liu_sigmod26,
title = {{Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure}},
author = {Liu, Shuainan and Ji, Tianxi and Fang, Zhongshuo and Wei, Lu and Li, Pan},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786680},
url = {https://dl.acm.org/doi/10.1145/3786680},
year = {2026}
}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 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 |
|---|---|---|---|---|
| 1,421 | PrivBasis: Frequent Itemset Mining with Differential Privacy | 2012 | VLDB | 0.00010828328 |
| 4,185 | Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics | 2017 | SIGMOD | 6.8462927e-05 |
| 5,908 | Differentially Private Binary- and Matrix-Valued Data Query: An XOR Mechanism | 2021 | VLDB | 6.0447537e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,172 | Weighted Fourier Factorizations: Optimal Gaussian Noise for Differentially Private Marginal and Product Queries | 2026 | PODS |
| 2 | 11,280 | Confidence Intervals for Private Query Processing | 2024 | VLDB |
| 3 | 9,545 | PrivRM: A Framework for Range Mean Estimation under Local Differential Privacy | 2025 | SIGMOD |
| 4 | 1,837 | Marginal Release Under Local Differential Privacy | 2018 | SIGMOD |
| 5 | 10,550 | Understanding Disclosure Risk in Differential Privacy with Applications to Noise Calibration and Auditing | 2026 | VLDB |
| 6 | 7,968 | Optimizing Fitness-For-Use of Differentially Private Linear Queries | 2021 | VLDB |
| 7 | 13,406 | High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data | 2022 | PODS |
| 8 | 10,451 | Enhancing Local Differential Privacy Accuracy by Exploiting Inherent Uncertainty | 2026 | SIGMOD |
| 9 | 7,517 | Private Incremental Regression | 2017 | PODS |
| 10 | 775 | Differentially Private Data Cubes: Optimizing Noise Sources and Consistency | 2011 | SIGMOD |