公开(公告)号：US20200311306A1

公开(公告)日：2020-10-01

申请号：US16771359

申请日：2019-01-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sungwook KIM ,  Hyejin SHIN ,  Soohyung KIM ,  Chunghun BAEK ,  Junbum SHIN ,  Youngeun LEE ,  Kyungsun CHO

IPC: G06F21/62 ,  G06F21/64 ,  G06F21/60 ,  G06F21/16

Abstract: Disclosed are an electronic device for obfuscating user data and a server for decoding the same. A method for controlling an electronic device according to the present disclosure comprises the steps of: acquiring a security parameter according to data transmitted to an external server; applying an obfuscation algorithm to the data by using the security parameter; and transmitting the data, to which the obfuscation algorithm has been applied, to the external server. Furthermore, in connection with a method for controlling a system comprising an electronic device for obfuscating data and a server for decoding the same according to the present disclosure, a method for controlling the electronic device comprises the steps of: inserting a fingerprint into data; generating multiple pieces of split data having a preset first size on the basis of the data into which the fingerprint has been inserted; applying an obfuscation algorithm to one piece of split data selected from the multiple pieces of split data by using a preset security parameter; and transmitting the split data, to which the obfuscation algorithm has been applied, to the server. In addition, a method for controlling the server comprises the steps of: receiving the multiple pieces of split data, to which the obfuscation algorithm has been applied, from the electronic device; acquiring at least one piece of candidate data on the basis of the received multiple pieces of split data, to which the obfuscation algorithm has been applied; and acquiring data comprising the fingerprint among the at least one piece of candidate data.

公开(公告)号：US20230076024A1

公开(公告)日：2023-03-09

申请号：US17986519

申请日：2022-11-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chunghun BAEK ,  Sungwook KIM ,  Soohyung KIM ,  Dongkyun NAM

IPC: G06N20/00 ,  H04L9/30 ,  H04L9/08

Abstract: Embodiments of the disclosure relate to an electronic device and a server for federated learning, and a method of the same. A method of refining a core artificial intelligence (AI) model built in the server includes transmitting, to each of a plurality of electronic devices performing federated learning with the core AI model, data for requesting transmission of first data used for refining the core AI model, receiving first data from at least one of the plurality of electronic devices, identifying an electronic device that has transmitted the first data from among the plurality of electronic devices, transmitting data for requesting transmission of second data to the electronic device that has transmitted the first data among the plurality of electronic devices, receiving second data from the electronic device that has transmitted the first data, and refining the core AI model by using the first data and the second data, wherein the first data includes first differential privacy protection data for protecting private data of each of the plurality of electronic devices, and the second data includes differential privacy modification data used to modify the first differential privacy protection data into second differential privacy protection data.