Complex Encoded Tile Tensors: Accelerating Encrypted Analytics

Ehud Aharoni; Nir Drucker; Gilad Ezov; Hayim Shaul; Omri Soceanu

doi:10.1109/msec.2022.3181689

Complex Encoded Tile Tensors: Accelerating Encrypted Analytics

Ehud Aharoni, Nir Drucker, Gilad Ezov, Hayim Shaul, Omri Soceanu

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

Abstract

Homomorphic encryption enables private artificial intelligence computations to be run on the cloud. Recent work used tile tensors to speed up the evaluation of neural network inference. We introduce an extension to tile tensors for the complex plane, resulting in an ∼ 1.68 × amortized speedup.

Original language	English
Pages (from-to)	35-43
Number of pages	9
Journal	IEEE Security and Privacy
Volume	20
Issue number	5
DOIs	https://doi.org/10.1109/msec.2022.3181689
State	Published - 2022
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2003-2012 IEEE.

ASJC Scopus subject areas

Computer Networks and Communications
Electrical and Electronic Engineering
Law

Access to Document

10.1109/msec.2022.3181689

Cite this

@article{9fce8f76ba3640899ae54af9f4a7b9e4,

title = "Complex Encoded Tile Tensors: Accelerating Encrypted Analytics",

abstract = "Homomorphic encryption enables private artificial intelligence computations to be run on the cloud. Recent work used tile tensors to speed up the evaluation of neural network inference. We introduce an extension to tile tensors for the complex plane, resulting in an ∼ 1.68 × amortized speedup.",

author = "Ehud Aharoni and Nir Drucker and Gilad Ezov and Hayim Shaul and Omri Soceanu",

note = "Publisher Copyright: {\textcopyright} 2003-2012 IEEE.",

year = "2022",

doi = "10.1109/msec.2022.3181689",

language = "English",

volume = "20",

pages = "35--43",

journal = "IEEE Security and Privacy",

issn = "1540-7993",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - Complex Encoded Tile Tensors

T2 - Accelerating Encrypted Analytics

AU - Aharoni, Ehud

AU - Drucker, Nir

AU - Ezov, Gilad

AU - Shaul, Hayim

AU - Soceanu, Omri

PY - 2022

Y1 - 2022

N2 - Homomorphic encryption enables private artificial intelligence computations to be run on the cloud. Recent work used tile tensors to speed up the evaluation of neural network inference. We introduce an extension to tile tensors for the complex plane, resulting in an ∼ 1.68 × amortized speedup.

AB - Homomorphic encryption enables private artificial intelligence computations to be run on the cloud. Recent work used tile tensors to speed up the evaluation of neural network inference. We introduce an extension to tile tensors for the complex plane, resulting in an ∼ 1.68 × amortized speedup.

UR - http://www.scopus.com/inward/record.url?scp=85133802443&partnerID=8YFLogxK

U2 - 10.1109/msec.2022.3181689

DO - 10.1109/msec.2022.3181689

M3 - Article

AN - SCOPUS:85133802443

SN - 1540-7993

VL - 20

SP - 35

EP - 43

JO - IEEE Security and Privacy

JF - IEEE Security and Privacy

IS - 5

ER -

Complex Encoded Tile Tensors: Accelerating Encrypted Analytics

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this