IP Library › Granted Patent US 12,373,609
Granted Patent B2
US 12,373,609 · App. 17/788,739 · Granted Jul 29, 2025

Conversion device for secure computation, secure computation system, conversion method for secure computation and conversion program for secure computation

Inventors: Hiroki Imabayashi (Tokyo, JP); Kentaro Mihara (Tokyo, JP)
Assignee: EAGLYS Inc.
G06F21/71
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,373,609
App. No.
17/788,739
Granted
Jul 29, 2025
Kind
B2
Abstract

A conversion device for secure computation for converting an input data which is an object data of secure computation into an input format applicable to the secure computation is provided. A conversion device for secure computation of the present invention includes an acquisition unit configured to acquire an object data of the secure computation; a storage unit configured to store a correspondence table specifying an input format required for executing the secure computation; a conversion processing unit configured to perform a conversion from the acquired object data into a secure computation data in accordance with the correspondence table; and an output unit configured to output the secure computation data.

Claims (55)

1. A conversion device for secure computation comprising:

an acquisition unit configured to acquire an object data of the secure computation;

a storage unit configured to store a correspondence table specifying an input format required for executing the secure computation;

a conversion processing unit configured to perform a conversion from the acquired object data into a secure computation data in accordance with the correspondence table; and

an output unit configured to output the secure computation data, wherein

the object data at least includes a second data which relates to a machine learning of a first data, and

the second data includes a specification data of the machine learning of the first data,

a specification of the machine learning and the input format are associated with each other in the correspondence table, and

the conversion processing unit is configured to extract the input format corresponding to the specification data of the machine learning from the stored correspondence table and perform the conversion in accordance with the extracted input format.

2. The conversion device for secure computation according to claim 1 , wherein

the acquisition unit is configured to acquire a request condition data for the secure computation, and

the conversion processing unit is configured to perform the conversion in accordance with the input format selected based on the request condition data in the extracted input format.

3. The conversion device for secure computation according to claim 2 , wherein

the specification data of the machine learning includes an information related to an algorithm used in the machine learning or a source code.

4. The conversion device for secure computation according to claim 3 , wherein

the object data includes a data obtained by performing the machine learning on the first data, and

the conversion processing unit includes an encryption unit configured to encrypt the data obtained by performing the machine learning in accordance with an encryption method specified in the selected input format as the conversion.

5. The conversion device for secure computation according to claim 3 , wherein

the object data includes the first data,

the conversion processing unit includes an encryption unit configured to encrypt the first data in accordance with an encryption method specified in the selected input format as the conversion.

6. The conversion device for secure computation according to claim 5 , wherein

the request condition data includes a selective condition related to the secure computation or a plurality of evaluation conditions to which a score is given, and

the conversion processing unit is configured to perform the conversion in accordance with the input format selected based on the selective condition and/or the score.

7. The conversion device for secure computation according to claim 6 , wherein

the evaluation conditions include a condition related to at least one of a processing speed, a security level and a cost, and

the evaluation conditions are configured to be input via a graphical user interface.

8. The conversion device for secure computation according to claim 6 , wherein

the storage unit is configured to store the request condition data and the input format of the conversion performed in accordance with the request condition data,

a learning unit configured to learn a relation between the stored request condition data and the input format of the conversion performed in accordance with the request condition data is further provided, and

the conversion processing unit is configured to perform the conversion in accordance with the learned relation.

9. The conversion device for secure computation according to claim 1 , wherein

the input format is a data specified by any one of or a combination of an encryption type, an encryption scheme, a unit of a data to be encrypted, a data structure, a processing protocol and an architecture for the secure computation.

10. A secure computation system comprising:

a processing request unit configured to transmit a processing request of an object data of a secure computation;

a secure computation conversion unit; and

a secure computation execution unit, wherein

the secure computation conversion unit includes:

an acquisition unit configured to acquire the object data via the processing request unit;

a storage unit configured to store a correspondence table specifying an input format required for executing the secure computation;

a conversion processing unit configured to perform a conversion from the acquired object data into a secure computation data in accordance with the correspondence table; and

an output unit configured to output the secure computation data to the secure computation execution unit, wherein

the object data at least includes a second data which relates to a machine learning of a first data, and

the second data includes a specification data of the machine learning of the first data,

a specification of the machine learning and the input format are associated with each other in the correspondence table, and

the conversion processing unit is configured to extract the input format corresponding to the specification data of the machine learning from the stored correspondence table and perform the conversion in accordance with the extracted input format.

11. A conversion method for converting an object data of secure computation into a secure computation data, the conversion method being executed by a computer having a control unit and a storage unit,

the conversion method comprising:

a step of acquiring the object data of the secure computation by the control unit;

a step of storing a correspondence table specifying an input format required for executing the secure computation in the storage unit by the control unit;

a step of performing a conversion from the acquired object data into a secure computation data in accordance with the correspondence table by the control unit; and

a step of outputting the secure computation data by the control unit, wherein

the object data at least includes a second data which relates to a machine learning of a first data, and

the second data includes a specification data of the machine learning of the first data,

a specification of the machine learning and the input format are associated with each other in the correspondence table, and

the conversion processing unit is configured to extract the input format corresponding to the specification data of the machine learning from the stored correspondence table and perform the conversion in accordance with the extracted input format.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 24, 2022
From: IMABAYASHI, HIROKI; MIHARA, KENTARO
To: EAGLYS INC.
Reel/Frame 060298/0315 →
Priority Claims (1)
JP 2020-010145 · Jan 24, 2020 · national
Continuity (1)
Related Publication 20230041118A1 · Feb 9, 2023
References Cited (16)
US 20060112331A1 · Ashida et al. · 2006 [cited by applicant]
US 20180268296A1 · Zheng et al. · 2018 [cited by applicant]
US 20200019867A1 · Nandakumar et al. · 2020 [cited by applicant]
US 20210358332A1 · Mishina · 2021 [cited by examiner]
JP 2006146677A · 2006 [cited by applicant]
JP 2010287055A · 2010 [cited by applicant]
JP 6549332B · 2019 [cited by applicant]
Supplementary European Search Report dated May 31, 2023. [cited by applicant]
Communication pursuant to Article 94(3) EPC dated Jun. 9, 2023. [cited by applicant]
Shaik Imtiyazuddin, et al., “A Recommender System for Efficient Implementation of Privacy Preserving Machine Learning Primitives Base on FHE”,Cyber Security Cryptography and Machine Learning: Fourth International Sympos… [cited by applicant]
Communication pursuant to Article 94(3) EPC dated Nov. 23, 2023. [cited by applicant]
Yu Ishimaki, et al., “Privacy-Preserving String Search for Genome Sequences with FHE bootstrapping optimization”, 2016 IEEE International Conference on Big Data (Big Data), Dec. 5, 2016, pp. 3989-3991. [cited by applicant]
International Search Report for PCT/JP2021/000494 dated Mar. 16, 2021. [cited by applicant]
PCT written opinion dated Mar. 16, 2021. [cited by applicant]
Vladimir Kolesnikov, et al., “From Dust to Dawn: Practically Efficient Two-Party Secure Function Evaluation Protocols and their Modular Design”, Cryptology ePrint Archive, [online], 2013. [cited by applicant]
Chiraag Juvekar, et al., “Gazelle: A Low Latency Framework for Secure Neural Network Inference”, Cryptology ePrint Archive, [online], 2018. [cited by applicant]