Adversarially Robust Streaming Algorithms via Differential Privacy

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

A streaming algorithm is said to be adversarially robust if its accuracy guarantees are maintained even when the data stream is chosen maliciously, by an adaptive adversary. We establish a connection between adversarial robustness of streaming algorithms and the notion of differential privacy. This connection allows us to design new adversarially robust streaming algorithms that outperform the current state-of-The-Art constructions for many interesting regimes of parameters.

Original languageEnglish
Article number42
JournalJournal of the ACM
Volume69
Issue number6
DOIs
StatePublished - 24 Nov 2022

Funding

FundersFunder number
Yandex Initiative for Machine Learning1871/19
Horizon 2020 Framework Programme882396, 993/17
Horizon 2020 Framework Programme
Blavatnik Family Foundation
European Research Council
Israel Science Foundation1595/19
Israel Science Foundation
Tel Aviv University

    Keywords

    • Streaming
    • differential privacy
    • robustness

    Fingerprint

    Dive into the research topics of 'Adversarially Robust Streaming Algorithms via Differential Privacy'. Together they form a unique fingerprint.

    Cite this