Adversarially robust streaming algorithms via differential privacy

Avinatan Hassidim; Haim Kaplan; Yishay Mansour; Yossi Matias; Uri Stemmer

Adversarially robust streaming algorithms via differential privacy

Avinatan Hassidim
, Haim Kaplan
, Yishay Mansour
, Yossi Matias
, Uri Stemmer

Research output: Contribution to journal › Conference article › peer-review

51 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 language	English
Journal	Advances in Neural Information Processing Systems
Volume	2020-December
State	Published - 1 Jan 2020
Event	34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online Duration: 6 Dec 2020 → 12 Dec 2020

ASJC Scopus subject areas

Signal Processing
Information Systems
Computer Networks and Communications

Cite this

@article{4f84349d278b45178b278637a2be0509,

title = "Adversarially robust streaming algorithms via differential privacy",

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.",

author = "Avinatan Hassidim and Haim Kaplan and Yishay Mansour and Yossi Matias and Uri Stemmer",

note = "Publisher Copyright: {\textcopyright} 2020 Neural information processing systems foundation. All rights reserved.; 34th Conference on Neural Information Processing Systems, NeurIPS 2020 ; Conference date: 06-12-2020 Through 12-12-2020",

year = "2020",

month = jan,

day = "1",

language = "English",

volume = "2020-December",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - Adversarially robust streaming algorithms via differential privacy

AU - Hassidim, Avinatan

AU - Kaplan, Haim

AU - Mansour, Yishay

AU - Matias, Yossi

AU - Stemmer, Uri

PY - 2020/1/1

Y1 - 2020/1/1

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85101611257

M3 - Conference article

AN - SCOPUS:85101611257

SN - 1049-5258

VL - 2020-December

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 34th Conference on Neural Information Processing Systems, NeurIPS 2020

Y2 - 6 December 2020 through 12 December 2020

ER -

Adversarially robust streaming algorithms via differential privacy

Abstract

ASJC Scopus subject areas

Fingerprint

Cite this