Private Decision Tree Evaluation by a Single Untrusted Server for Machine Learnig as a Service

Yoshifumi SAITO; Wakaha OGATA

doi:10.1587/transfun.2021CIP0004

IEICE TRANSACTIONS on Fundamentals

Private Decision Tree Evaluation by a Single Untrusted Server for Machine Learnig as a Service

Yoshifumi SAITO, Wakaha OGATA

Full Text Views

0

Cite this

Summary :

In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E105-A No.3 pp.203-213

Publication Date: 2022/03/01

Publicized: 2021/09/17

Online ISSN: 1745-1337

DOI: 10.1587/transfun.2021CIP0004

Type of Manuscript: Special Section PAPER (Special Section on Cryptography and Information Security)

Category

Authors

Yoshifumi SAITO
Tokyo Institute of Technology
Wakaha OGATA
Tokyo Institute of Technology

Keyword

privacy preserving, decision tree evaluation, fully homomorphic encryption, secure multiparty computation

Cite this

Copy

Yoshifumi SAITO, Wakaha OGATA, "Private Decision Tree Evaluation by a Single Untrusted Server for Machine Learnig as a Service" in IEICE TRANSACTIONS on Fundamentals, vol. E105-A, no. 3, pp. 203-213, March 2022, doi: 10.1587/transfun.2021CIP0004.
Abstract: In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021CIP0004/_p

Copy

@ARTICLE{e105-a_3_203,
author={Yoshifumi SAITO, Wakaha OGATA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Private Decision Tree Evaluation by a Single Untrusted Server for Machine Learnig as a Service},
year={2022},
volume={E105-A},
number={3},
pages={203-213},
abstract={In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.},
keywords={},
doi={10.1587/transfun.2021CIP0004},
ISSN={1745-1337},
month={March},}

Copy

TY - JOUR
TI - Private Decision Tree Evaluation by a Single Untrusted Server for Machine Learnig as a Service
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 203
EP - 213
AU - Yoshifumi SAITO
AU - Wakaha OGATA
PY - 2022
DO - 10.1587/transfun.2021CIP0004
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 3
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - March 2022
AB - In this paper, we propose the first private decision tree evaluation (PDTE) schemes which are suitable for use in Machine Learning as a Service (MLaaS) scenarios. In our schemes, a user and a model owner send the ciphertexts of a sample and a decision tree model, respectively, and a single server classifies the sample without knowing the sample nor the decision tree. Although many PDTE schemes have been proposed so far, most of them require to reveal the decision tree to the server. This is undesirable because the classification model is the intellectual property of the model owner, and/or it may include sensitive information used to train the model, and therefore the model also should be hidden from the server. In other PDTE schemes, multiple servers jointly conduct the classification process and the decision tree is kept secret from the servers under the assumption they do not collude. Unfortunately, this assumption may not hold because MLaaS is usually provided by a single company. In contrast, our schemes do not have such problems. In principle, fully homomorphic encryption allows us to classify an encrypted sample based on an encrypted decision tree, and in fact, the existing non-interactive PDTE scheme can be modified so that the server classifies only handling ciphertexts. However, the resulting scheme is less efficient than ours. We also show the experimental results for our schemes.
ER -

IEICE TRANSACTIONS on Fundamentals