Adversarially Robust Streaming Algorithms via Differential Privacy

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

doi:10.1145/3556972

Adversarially Robust Streaming Algorithms via Differential Privacy

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

Bar-Ilan University, Tel Aviv University

Research output: Contribution to journal › Article › peer-review

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
Article number	42
Journal	Journal of the ACM
Volume	69
Issue number	6
DOIs	https://doi.org/10.1145/3556972
State	Published - 24 Nov 2022

Keywords

Streaming
differential privacy
robustness

All Science Journal Classification (ASJC) codes

Software
Control and Systems Engineering
Information Systems
Hardware and Architecture
Artificial Intelligence

Access to Document

10.1145/3556972

Cite this

@article{4f18dd514a54434da792526e553e661a,

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.",

keywords = "Streaming, differential privacy, robustness",

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

note = "Publisher Copyright: {\textcopyright} 2022 Copyright held by the owner/author(s).",

year = "2022",

month = nov,

day = "24",

doi = "10.1145/3556972",

language = "الإنجليزيّة",

volume = "69",

journal = "Journal of the ACM",

issn = "0004-5411",

publisher = "Association for Computing Machinery (ACM)",

number = "6",

}

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 - 2022/11/24

Y1 - 2022/11/24

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.

KW - Streaming

KW - differential privacy

KW - robustness

UR - http://www.scopus.com/inward/record.url?scp=85146365747&partnerID=8YFLogxK

U2 - 10.1145/3556972

DO - 10.1145/3556972

M3 - مقالة

SN - 0004-5411

VL - 69

JO - Journal of the ACM

JF - Journal of the ACM

IS - 6

M1 - 42

ER -

Adversarially Robust Streaming Algorithms via Differential Privacy

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this