The authors design a scalable DP stream processing system called DP-SQLP that can handle large-scale industrial workloads. Key highlights:
DP-SQLP is built using a streaming framework similar to Spark Streaming, and is built on top of the Spanner database and the F1 query engine from Google.
The authors make algorithmic advances to address challenges in the streaming setting, including:
The authors empirically demonstrate the efficacy of DP-SQLP, obtaining at least 16x reduction in error over meaningful baselines.
DP-SQLP is implemented for a streaming differentially private user impressions for Google Shopping, and the streaming DP algorithms are further applied to Google Trends.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Bing Zhang,V... at arxiv.org 04-08-2024
https://arxiv.org/pdf/2303.18086.pdfDeeper Inquiries