Doing real work with FHE: The case of logistic regression

Jack L.H. Crawford; Craig Gentry; Shai Halevi; Daniel Platt; Victor Shoup

doi:10.1145/3267973.3267974

Doing real work with FHE: The case of logistic regression

Jack L.H. Crawford, Craig Gentry, Shai Halevi, Daniel Platt, Victor Shoup

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We describe our recent experience, building a system that uses fully-homomorphic encryption (FHE) to approximate the coefficients of a logistic-regression model, built from genomic data. The aim of this project was to examine the feasibility of a solution that operates "deep within the bootstrapping regime," solving a problem that appears too hard to be addressed just with somewhat-homomorphic encryption. As part of this project, we implemented optimized versions of many bread and butter FHE tools. These tools include binary arithmetic, comparisons, partial sorting, and low-precision approximation of arbitrary functions (used for reciprocals, logarithms, etc.). Our solution can handle thousands of records and hundreds of fields, and it takes a few hours to run. To achieve this performance we had to be extremely frugal with expensive bootstrapping and data-movement operations. We believe that our experience in this project could serve as a guide for what is or is not currently feasible to do with fully-homomorphic encryption.

Original language	English (US)
Title of host publication	WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018
Publisher	Association for Computing Machinery
Pages	1-12
Number of pages	12
ISBN (Electronic)	9781450359870
DOIs	https://doi.org/10.1145/3267973.3267974
State	Published - Oct 15 2018
Event	6th Annual Workshop on Encrypted Computing and Applied Homomorphic Cryptography. WAHC 208, co-located with CCS 2018 - Toronto, Canada Duration: Oct 19 2018 → …

Publication series

Name	Proceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)	1543-7221

Other

Other	6th Annual Workshop on Encrypted Computing and Applied Homomorphic Cryptography. WAHC 208, co-located with CCS 2018
Country	Canada
City	Toronto
Period	10/19/18 → …

Keywords

Homomorphic encryption
Implementation
Logistic regression
Private genomic computation

ASJC Scopus subject areas

Software
Computer Networks and Communications

Access to Document

10.1145/3267973.3267974

Fingerprint Dive into the research topics of 'Doing real work with FHE: The case of logistic regression'. Together they form a unique fingerprint.

Cite this

Crawford, J. L. H., Gentry, C., Halevi, S., Platt, D., & Shoup, V. (2018). Doing real work with FHE: The case of logistic regression. In WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018 (pp. 1-12). (Proceedings of the ACM Conference on Computer and Communications Security). Association for Computing Machinery. https://doi.org/10.1145/3267973.3267974

Doing real work with FHE : The case of logistic regression. / Crawford, Jack L.H.; Gentry, Craig; Halevi, Shai; Platt, Daniel; Shoup, Victor.

WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018. Association for Computing Machinery, 2018. p. 1-12 (Proceedings of the ACM Conference on Computer and Communications Security).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Crawford, JLH, Gentry, C, Halevi, S, Platt, D & Shoup, V 2018, Doing real work with FHE: The case of logistic regression. in WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018. Proceedings of the ACM Conference on Computer and Communications Security, Association for Computing Machinery, pp. 1-12, 6th Annual Workshop on Encrypted Computing and Applied Homomorphic Cryptography. WAHC 208, co-located with CCS 2018, Toronto, Canada, 10/19/18. https://doi.org/10.1145/3267973.3267974

Crawford JLH, Gentry C, Halevi S, Platt D, Shoup V. Doing real work with FHE: The case of logistic regression. In WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018. Association for Computing Machinery. 2018. p. 1-12. (Proceedings of the ACM Conference on Computer and Communications Security). https://doi.org/10.1145/3267973.3267974

Crawford, Jack L.H. ; Gentry, Craig ; Halevi, Shai ; Platt, Daniel ; Shoup, Victor. / Doing real work with FHE : The case of logistic regression. WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018. Association for Computing Machinery, 2018. pp. 1-12 (Proceedings of the ACM Conference on Computer and Communications Security).

@inproceedings{1725cd7e35fd43c3a1a1f186029eafeb,

title = "Doing real work with FHE: The case of logistic regression",

abstract = "We describe our recent experience, building a system that uses fully-homomorphic encryption (FHE) to approximate the coefficients of a logistic-regression model, built from genomic data. The aim of this project was to examine the feasibility of a solution that operates {"}deep within the bootstrapping regime,{"} solving a problem that appears too hard to be addressed just with somewhat-homomorphic encryption. As part of this project, we implemented optimized versions of many bread and butter FHE tools. These tools include binary arithmetic, comparisons, partial sorting, and low-precision approximation of arbitrary functions (used for reciprocals, logarithms, etc.). Our solution can handle thousands of records and hundreds of fields, and it takes a few hours to run. To achieve this performance we had to be extremely frugal with expensive bootstrapping and data-movement operations. We believe that our experience in this project could serve as a guide for what is or is not currently feasible to do with fully-homomorphic encryption.",

keywords = "Homomorphic encryption, Implementation, Logistic regression, Private genomic computation",

author = "Crawford, {Jack L.H.} and Craig Gentry and Shai Halevi and Daniel Platt and Victor Shoup",

year = "2018",

month = oct,

day = "15",

doi = "10.1145/3267973.3267974",

language = "English (US)",

series = "Proceedings of the ACM Conference on Computer and Communications Security",

publisher = "Association for Computing Machinery",

pages = "1--12",

booktitle = "WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018",

note = "6th Annual Workshop on Encrypted Computing and Applied Homomorphic Cryptography. WAHC 208, co-located with CCS 2018 ; Conference date: 19-10-2018",

}

TY - GEN

T1 - Doing real work with FHE

T2 - 6th Annual Workshop on Encrypted Computing and Applied Homomorphic Cryptography. WAHC 208, co-located with CCS 2018

AU - Crawford, Jack L.H.

AU - Gentry, Craig

AU - Halevi, Shai

AU - Platt, Daniel

AU - Shoup, Victor

PY - 2018/10/15

Y1 - 2018/10/15

N2 - We describe our recent experience, building a system that uses fully-homomorphic encryption (FHE) to approximate the coefficients of a logistic-regression model, built from genomic data. The aim of this project was to examine the feasibility of a solution that operates "deep within the bootstrapping regime," solving a problem that appears too hard to be addressed just with somewhat-homomorphic encryption. As part of this project, we implemented optimized versions of many bread and butter FHE tools. These tools include binary arithmetic, comparisons, partial sorting, and low-precision approximation of arbitrary functions (used for reciprocals, logarithms, etc.). Our solution can handle thousands of records and hundreds of fields, and it takes a few hours to run. To achieve this performance we had to be extremely frugal with expensive bootstrapping and data-movement operations. We believe that our experience in this project could serve as a guide for what is or is not currently feasible to do with fully-homomorphic encryption.

AB - We describe our recent experience, building a system that uses fully-homomorphic encryption (FHE) to approximate the coefficients of a logistic-regression model, built from genomic data. The aim of this project was to examine the feasibility of a solution that operates "deep within the bootstrapping regime," solving a problem that appears too hard to be addressed just with somewhat-homomorphic encryption. As part of this project, we implemented optimized versions of many bread and butter FHE tools. These tools include binary arithmetic, comparisons, partial sorting, and low-precision approximation of arbitrary functions (used for reciprocals, logarithms, etc.). Our solution can handle thousands of records and hundreds of fields, and it takes a few hours to run. To achieve this performance we had to be extremely frugal with expensive bootstrapping and data-movement operations. We believe that our experience in this project could serve as a guide for what is or is not currently feasible to do with fully-homomorphic encryption.

KW - Homomorphic encryption

KW - Implementation

KW - Logistic regression

KW - Private genomic computation

UR - http://www.scopus.com/inward/record.url?scp=85056810838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056810838&partnerID=8YFLogxK

U2 - 10.1145/3267973.3267974

DO - 10.1145/3267973.3267974

M3 - Conference contribution

AN - SCOPUS:85056810838

T3 - Proceedings of the ACM Conference on Computer and Communications Security

SP - 1

EP - 12

BT - WAHC 2018 - Proceedings of the 6th Workshop on Encrypted Computing and Applied Homomorphic Cryptography, co-located with CCS 2018

PB - Association for Computing Machinery

Y2 - 19 October 2018

ER -