Differentially Private Stream Processing at Scale
Summary: Introduces DP-SQLP, the first large-scale user-level differentially private streaming aggregation system, built on Spanner/F1. Its scalable unbounded-key selection, preemptive execution, and continual histograms enable billion-key streams and substantially lower error in Google deployments. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Bing Zhang (Google)
- 2. Vadym Doroshenko (Google)
- 3. Peter Kairouz (Google)
- 4. Thomas Steinke (Google)
- 5. Abhradeep Thakurta (Google)
- 6. Ziyin Ma (Google)
- 7. Eidan Cohen (Google)
- 8. Himani Apte (Google)
- 9. Jodi Spacek (Google)
BibTeX Citation
@article{zhang_vldb24,
title = {{Differentially Private Stream Processing at Scale}},
author = {Zhang, Bing and Doroshenko, Vadym and Kairouz, Peter and Steinke, Thomas and Thakurta, Abhradeep and Ma, Ziyin and Cohen, Eidan and Apte, Himani and Spacek, Jodi},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {12},
pages = {4145--4158},
doi = {10.14778/3685800.3685833},
url = {https://doi.org/10.14778/3685800.3685833},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,334 | Continual Observation of Joins under Differential Privacy | 2024 | SIGMOD | 5.3527996e-05 |
| 10,828 | Toward Temporal Attribution Analytics in Dataflows | 2026 | VLDB | 4.9793485e-05 |
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 |
|---|---|---|---|---|
| 325 | The Dataflow Model: A Practical Approach to Balancing Correctness, Latency, and Cost in Massive-Scale, Unbounded, Out-of-Order Data Processing | 2015 | VLDB | 0.00020964941 |
| 429 | Flexible Time Management in Data Stream Systems | 2004 | PODS | 0.00018439857 |
| 2,915 | F1 Query: Declarative Querying at Scale | 2018 | VLDB | 7.8616593e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,439 | A Nearly Instance-optimal Differentially Private Mechanism for Conjunctive Queries | 2022 | PODS |
| 2 | 10,501 | Sketch-based Secure Query Processing for Streaming Data | 2026 | SIGMOD |
| 3 | 8,823 | Scalable Delivery of Stream Query Result | 2009 | VLDB |
| 4 | 276 | Towards Practical Differential Privacy for SQL Queries | 2018 | VLDB |
| 5 | 11,636 | DOP-SQL: A General-purpose, High-utility, and Extensible Private SQL System | 2024 | VLDB |
| 6 | 7,694 | Local Differentially Private Heavy Hitter Detection in Data Streams with Bounded Memory | 2024 | SIGMOD |
| 7 | 10,660 | MTSP-LDP: A Framework for Multi-Task Streaming Data Publication under Local Differential Privacy | 2026 | SIGMOD |
| 8 | 10,539 | A General Framework for Per-record Differential Privacy | 2026 | SIGMOD |
| 9 | 10,440 | DP-S4S: Accurate and Scalable Select-Join-Aggregate Query Processing with User-Level Differential Privacy | 2026 | SIGMOD |
| 10 | 7,295 | Architecting a Differentially Private SQL Engine | 2019 | CIDR |