公开(公告)号：US20230198759A1

公开(公告)日：2023-06-22

申请号：US18172747

申请日：2023-02-22

Applicant: Samsung Electronics Co., Ltd. ,  KOREA UNIVERSITY RESEARCH AND BUSINESS FOUNDATION

Inventor： Dongwook SHIM ,  Donghoon LEE

IPC: H04L9/32 ,  G06F3/06

CPC classification number: H04L9/32 ,  G06F3/0622 ,  G06F3/0637 ,  G06F3/0673

Abstract: An electronic device is provided. The electronic device includes a memory and a processor, the processor allocates first and second address spaces (AS) to the memory in rich execution environment (REE) when detecting a request to write data, writes the data to the first AS and detect access to the second address space in the REE, configures access permission of a first user virtual memory AS (VMAS), mapped to the first address space, in the REE so that write access is deactivated by a trusted environment manager when detecting access to the second AS, configures access permission of a second user VMAS, mapped to the second AS, in the REE so that read access is activated and write access is deactivated, and configures access permission of a first kernel VMAS, mapped to the first AS, in the REE so that write access is deactivated by the trusted environment manager.

公开(公告)号：US20250132929A1

公开(公告)日：2025-04-24

申请号：US18990175

申请日：2024-12-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jungha PAIK ,  Dongmin KIM ,  Bumhan KIM ,  Hyeongseok KIM ,  Dongwook SHIM ,  Dasom LEE

IPC: H04L9/32 ,  G06N3/098 ,  H04L9/14

Abstract: A server intermediating federated learning, a user device, and a system including the server and the user device are disclosed. An intermediate server receives a global model from a central server to transmit the global model to a plurality of user devices. The intermediate server updates the global model based on a plurality of local models received respectively from the plurality of user devices in response to the transmission of the global model. One or more of the plurality of user devices includes a machine learning core to generate a local model by training the global model. The global model and individual data of a user device input into the machine learning core are encrypted or decrypted based on whether a key manager is comprised in the machine learning core.