Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation. / Cock, M. De; Dowsley, R.; Horst, C.; Katti, R.; Nascimento, A.; Poon, W. S.; Truex, S.

In: IEEE Transactions on Dependable and Secure Computing, Vol. 16, No. 2, 7873244, 03.2019, p. 217-230.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

Cock, MD, Dowsley, R, Horst, C, Katti, R, Nascimento, A, Poon, WS & Truex, S 2019, 'Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation', IEEE Transactions on Dependable and Secure Computing, vol. 16, no. 2, 7873244, pp. 217-230. https://doi.org/10.1109/TDSC.2017.2679189

APA

Cock, M. D., Dowsley, R., Horst, C., Katti, R., Nascimento, A., Poon, W. S., & Truex, S. (2019). Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation. IEEE Transactions on Dependable and Secure Computing, 16(2), 217-230. [7873244]. https://doi.org/10.1109/TDSC.2017.2679189

CBE

Cock MD, Dowsley R, Horst C, Katti R, Nascimento A, Poon WS, Truex S. 2019. Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation. IEEE Transactions on Dependable and Secure Computing. 16(2):217-230. https://doi.org/10.1109/TDSC.2017.2679189

MLA

Vancouver

Cock MD, Dowsley R, Horst C, Katti R, Nascimento A, Poon WS et al. Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation. IEEE Transactions on Dependable and Secure Computing. 2019 Mar;16(2):217-230. 7873244. https://doi.org/10.1109/TDSC.2017.2679189

Author

Cock, M. De ; Dowsley, R. ; Horst, C. ; Katti, R. ; Nascimento, A. ; Poon, W. S. ; Truex, S. / Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation. In: IEEE Transactions on Dependable and Secure Computing. 2019 ; Vol. 16, No. 2. pp. 217-230.

Bibtex

@article{3b6cf693640a43bd9115d2f6da3e78b3,
title = "Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation",
abstract = "Many data-driven personalized services require that private data of users is scored against a trained machine learning model. In this paper we propose a novel protocol for privacy-preserving classification of decision trees, a popular machine learning model in these scenarios. Our solutions is composed out of building blocks, namely a secure comparison protocol, a protocol for obliviously selecting inputs, and a protocol for multiplication. By combining some of the building blocks for our decision tree classification protocol, we also improve previously proposed solutions for classification of support vector machines and logistic regression models. Our protocols are information theoretically secure and, unlike previously proposed solutions, do not require modular exponentiations. We show that our protocols for privacy-preserving classification lead to more efficient results from the point of view of computational and communication complexities. We present accuracy and runtime results for seven classification benchmark datasets from the UCI repository.",
keywords = "Computational modeling, Cryptography, Data models, Decision trees, Logistics, Protocols, Private classification, decision trees, logistic regression, privacy-preserving computation, secret sharing, secure multiparty computation, support vector machines",
author = "Cock, {M. De} and R. Dowsley and C. Horst and R. Katti and A. Nascimento and Poon, {W. S.} and S. Truex",
year = "2019",
month = mar,
doi = "10.1109/TDSC.2017.2679189",
language = "English",
volume = "16",
pages = "217--230",
journal = "IEEE Transactions on Dependable and Secure Computing",
issn = "1545-5971",
publisher = "Institute of Electrical and Electronics Engineers",
number = "2",

}

RIS

TY - JOUR

T1 - Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models based on Pre-Computation

AU - Cock, M. De

AU - Dowsley, R.

AU - Horst, C.

AU - Katti, R.

AU - Nascimento, A.

AU - Poon, W. S.

AU - Truex, S.

PY - 2019/3

Y1 - 2019/3

N2 - Many data-driven personalized services require that private data of users is scored against a trained machine learning model. In this paper we propose a novel protocol for privacy-preserving classification of decision trees, a popular machine learning model in these scenarios. Our solutions is composed out of building blocks, namely a secure comparison protocol, a protocol for obliviously selecting inputs, and a protocol for multiplication. By combining some of the building blocks for our decision tree classification protocol, we also improve previously proposed solutions for classification of support vector machines and logistic regression models. Our protocols are information theoretically secure and, unlike previously proposed solutions, do not require modular exponentiations. We show that our protocols for privacy-preserving classification lead to more efficient results from the point of view of computational and communication complexities. We present accuracy and runtime results for seven classification benchmark datasets from the UCI repository.

AB - Many data-driven personalized services require that private data of users is scored against a trained machine learning model. In this paper we propose a novel protocol for privacy-preserving classification of decision trees, a popular machine learning model in these scenarios. Our solutions is composed out of building blocks, namely a secure comparison protocol, a protocol for obliviously selecting inputs, and a protocol for multiplication. By combining some of the building blocks for our decision tree classification protocol, we also improve previously proposed solutions for classification of support vector machines and logistic regression models. Our protocols are information theoretically secure and, unlike previously proposed solutions, do not require modular exponentiations. We show that our protocols for privacy-preserving classification lead to more efficient results from the point of view of computational and communication complexities. We present accuracy and runtime results for seven classification benchmark datasets from the UCI repository.

KW - Computational modeling

KW - Cryptography

KW - Data models

KW - Decision trees

KW - Logistics

KW - Protocols

KW - Private classification

KW - decision trees

KW - logistic regression

KW - privacy-preserving computation

KW - secret sharing

KW - secure multiparty computation

KW - support vector machines

UR - http://www.scopus.com/inward/record.url?scp=85063012297&partnerID=8YFLogxK

U2 - 10.1109/TDSC.2017.2679189

DO - 10.1109/TDSC.2017.2679189

M3 - Journal article

VL - 16

SP - 217

EP - 230

JO - IEEE Transactions on Dependable and Secure Computing

JF - IEEE Transactions on Dependable and Secure Computing

SN - 1545-5971

IS - 2

M1 - 7873244

ER -