ELECTRONIC DEVICE FOR PERFORMING FEDERATED LEARNING USING HARDWARE SECURE ARCHITECTURE AND FEDERATED LEARNING METHOD USING THE SAME

    公开(公告)号:US20220237523A1

    公开(公告)日:2022-07-28

    申请号:US17582873

    申请日:2022-01-24

    Abstract: Provided are an electronic device and server for performing federated learning, and a method of controlling the same for federated learning. A method, performed by the server, of performing federated learning with the electronic device, includes: transmitting, to the electronic device, requesting data requesting transmission of a federated learning parameter used to refine a core artificial intelligence model built in the server; receiving, from the electronic device, federated learning data including the federated learning parameter; identifying whether a result of federated learning performed by the electronic device is trustable, based on the federated learning data; and refining the core artificial intelligence model, based on a result of the identifying, wherein the receiving of the federated learning data includes receiving federated learning secure data stored in a hardware secure architecture of the electronic device, and the identifying of whether the result of the federated learning is trustable includes identifying whether the result of the federated learning is trustable, based on the federated learning secure data.

    ELECTRONIC APPARATUS AND CONTROL METHOD THEREOF

    公开(公告)号:US20210232368A1

    公开(公告)日:2021-07-29

    申请号:US17155558

    申请日:2021-01-22

    Abstract: An electronic apparatus and a control method of the electronic apparatus is provided. The method includes acquiring source code written in a programing language, identifying a structure including a function pointer from the source code, identifying a plurality of initialized variables as a plurality first variables among variables of the function pointer included in the identified structure, and modifying the source code by changing an indirect call using an unmodifiable variable among the plurality of first variables to a direct call.

Patent Agency Ranking