Title:
RISK CALCULATION DEVICE, RISK CALCULATION METHOD, AND RISK CALCULATION PROGRAM
Document Type and Number:
WIPO Patent Application WO/2024/079795
Kind Code:
A1
Abstract:
This risk calculation device constructs a plurality of first shadow models using a predetermined dataset. Then, the risk calculation device selects, from a set of sample data, pieces of sample data for which the average loss of the plurality of first shadow models is sufficiently large and the variance thereof is small. Subsequently, the risk calculation device constructs a plurality of second shadow models using the selected pieces of sample data and the dataset. Next, the risk calculation device calculates, for the pieces of sample data, a distance between the distribution of losses of the plurality of first shadow models and the distribution of losses of the plurality of second shadow models. Then, the risk calculation device selects sample data for which the distance is equal to or larger than a predetermined threshold value as sample data (target sample) to be used for calculating a privacy risk of a machine learning model.
Inventors:
SHIBAHARA TOSHIKI (JP)
MIURA TAKAYUKI (JP)
KII MASANOBU (JP)
ICHIKAWA ATSUNORI (JP)
MIURA TAKAYUKI (JP)
KII MASANOBU (JP)
ICHIKAWA ATSUNORI (JP)
Application Number:
PCT/JP2022/037926
Publication Date:
April 18, 2024
Filing Date:
October 11, 2022
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06F21/62; G06N20/00
Foreign References:
| CN113657762A | 2021-11-16 |
Other References:
CARLINI NICHOLAS, CHIEN STEVE, NASR MILAD, SONG SHUANG, TERZIS ANDREAS, TRAMER FLORIAN: "Membership Inference Attacks From First Principles", 2022 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP), IEEE, 12 April 2022 (2022-04-12) - 26 May 2022 (2022-05-26), pages 1897 - 1914, XP093009044, ISBN: 978-1-6654-1316-9, DOI: 10.1109/SP46214.2022.9833649
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: