Differentially Private Analysis on Graph Streams

Jalaj Upadhyay · Sarvagya Upadhyay · Raman Arora

Keywords: [ Ethics and Safety ] [ Privacy-preserving Statistics and Machine Learning ]

[ Abstract ]
Wed 14 Apr 12:45 p.m. PDT — 2:45 p.m. PDT
Oral presentation: Graphs and Networks
Wed 14 Apr 11:30 a.m. PDT — 12:30 p.m. PDT

Abstract: In this paper, we focus on answering queries, in a differentially private manner, on graph streams. We adopt the sliding window model of privacy, where we wish to perform analysis on the last $W$ updates and ensure that privacy is preserved for the entire stream. We show that in this model, the price of ensuring differential privacy is minimal. Furthermore, since differential privacy is preserved under post-processing, our results can be used as a subroutine in many tasks, including Lipschitz learning on graphs, cut functions, and spectral clustering.

Chat is not available.