Crypto-oriented neural architecture design

Avital Shafran; Gil Segev; Shmuel Peleg; Yedid Hoshen

doi:10.1109/ICASSP39728.2021.9413592

Crypto-oriented neural architecture design

Avital Shafran, Gil Segev, Shmuel Peleg, Yedid Hoshen

The Rachel and Selim Benin School of Engineering and Computer Science

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

2 Scopus citations

Abstract

Sending private data to Neural Network applications raises many privacy concerns. The cryptography community developed a variety of secure computation methods to address such privacy issues. As generic techniques for secure computation are typically prohibitively expensive, efforts focus on optimizing these cryptographic tools. Differently, we propose to optimize the design of crypto-oriented neural architectures, introducing a novel Partial Activation layer. The proposed layer is much faster for secure computation as it contains fewer non linear computations. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrates significant improvement to the efficiency of secure inference on common evaluation metrics.

Original language	American English
Pages (from-to)	2680-2684
Number of pages	5
Journal	Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Volume	2021-June
DOIs	https://doi.org/10.1109/ICASSP39728.2021.9413592
State	Published - 2021
Event	2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada Duration: 6 Jun 2021 → 11 Jun 2021

Bibliographical note

Funding Information:
This research has been supported by the Israel ministry of Science and Technology, by the Israel Science foundation, and by the European Union’s Horizon 2020 Framework Program (H2020) via an ERC Grant (Grant No. 714253).

Publisher Copyright:
© 2021 IEEE

Keywords

NN Architecture
Secure Inference

Access to Document

10.1109/ICASSP39728.2021.9413592

Cite this

@article{0a828ec626284b99bdeb9af3d0b818f3,

title = "Crypto-oriented neural architecture design",

abstract = "Sending private data to Neural Network applications raises many privacy concerns. The cryptography community developed a variety of secure computation methods to address such privacy issues. As generic techniques for secure computation are typically prohibitively expensive, efforts focus on optimizing these cryptographic tools. Differently, we propose to optimize the design of crypto-oriented neural architectures, introducing a novel Partial Activation layer. The proposed layer is much faster for secure computation as it contains fewer non linear computations. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrates significant improvement to the efficiency of secure inference on common evaluation metrics.",

keywords = "NN Architecture, Secure Inference",

author = "Avital Shafran and Gil Segev and Shmuel Peleg and Yedid Hoshen",

note = "Funding Information: This research has been supported by the Israel ministry of Science and Technology, by the Israel Science foundation, and by the European Union{\textquoteright}s Horizon 2020 Framework Program (H2020) via an ERC Grant (Grant No. 714253). Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 ; Conference date: 06-06-2021 Through 11-06-2021",

year = "2021",

doi = "10.1109/ICASSP39728.2021.9413592",

language = "American English",

volume = "2021-June",

pages = "2680--2684",

journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",

issn = "1520-6149",

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

}

TY - JOUR

T1 - Crypto-oriented neural architecture design

AU - Shafran, Avital

AU - Segev, Gil

AU - Peleg, Shmuel

AU - Hoshen, Yedid

N1 - Funding Information: This research has been supported by the Israel ministry of Science and Technology, by the Israel Science foundation, and by the European Union’s Horizon 2020 Framework Program (H2020) via an ERC Grant (Grant No. 714253). Publisher Copyright: © 2021 IEEE

PY - 2021

Y1 - 2021

N2 - Sending private data to Neural Network applications raises many privacy concerns. The cryptography community developed a variety of secure computation methods to address such privacy issues. As generic techniques for secure computation are typically prohibitively expensive, efforts focus on optimizing these cryptographic tools. Differently, we propose to optimize the design of crypto-oriented neural architectures, introducing a novel Partial Activation layer. The proposed layer is much faster for secure computation as it contains fewer non linear computations. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrates significant improvement to the efficiency of secure inference on common evaluation metrics.

AB - Sending private data to Neural Network applications raises many privacy concerns. The cryptography community developed a variety of secure computation methods to address such privacy issues. As generic techniques for secure computation are typically prohibitively expensive, efforts focus on optimizing these cryptographic tools. Differently, we propose to optimize the design of crypto-oriented neural architectures, introducing a novel Partial Activation layer. The proposed layer is much faster for secure computation as it contains fewer non linear computations. Evaluating our method on three state-of-the-art architectures (SqueezeNet, ShuffleNetV2, and MobileNetV2) demonstrates significant improvement to the efficiency of secure inference on common evaluation metrics.

KW - NN Architecture

KW - Secure Inference

UR - http://www.scopus.com/inward/record.url?scp=85114960683&partnerID=8YFLogxK

U2 - 10.1109/ICASSP39728.2021.9413592

DO - 10.1109/ICASSP39728.2021.9413592

M3 - Conference article

AN - SCOPUS:85114960683

SN - 1520-6149

VL - 2021-June

SP - 2680

EP - 2684

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021

Y2 - 6 June 2021 through 11 June 2021

ER -

Crypto-oriented neural architecture design

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this