公开(公告)号：US20220271933A1

公开(公告)日：2022-08-25

申请号：US17538451

申请日：2021-11-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Xun Chen ,  Jianwei Qian ,  Fanny F. Wong ,  Peter King ,  Sylvia Leung

IPC: H04L9/08 ,  G06F21/64 ,  H04L9/32

Abstract: A method executed by a first electronic device (ED1) includes splitting a selected secret for backup into a plurality of N secret shares in a trusted execution environment (TEE) of the ED1. The method includes transferring, via the transceiver over a short-range transmission, the N secret shares to N trustee devices, by transferring each secret share from among the N secret shares to a different trustee device from among the N trustee devices. Each secret share is configured to cause the trustee device to store the secret share in a TEE of a trustee device upon receipt by the trustee device. The method includes receiving, from the trustee device, one of an acknowledgement confirming the transferred secret share is stored in the TEE of the trustee device or an error warning the transferred secret share is not stored in the TEE of the trustee device.

公开(公告)号：US20220114014A1

公开(公告)日：2022-04-14

申请号：US17067532

申请日：2020-10-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Xun Chen ,  Jianwei Qian

IPC: G06F9/48 ,  G06F9/50 ,  G06F9/30 ,  G06N20/00 ,  G06K9/62

Abstract: An electronic device includes at least one transceiver, at least one memory, and at least one processor coupled to the at least one transceiver and the at least one memory. The at least one processor is configured to receive, via the at least one transceiver, an AI model in a trusted execution environment (TEE). The at least one processor is also configured to receive an inference request and input data from a source outside the TEE. The at least one processor is further configured to partition a calculation of an inference result between an internal calculation performed by processor resources within the TEE and an external calculation performed by processor resources outside the TEE. In addition, the at least one processor is configured to produce the inference result based on results of the internal calculation and the external calculation.

公开(公告)号：US12067144B2

公开(公告)日：2024-08-20

申请号：US17375976

申请日：2021-07-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jianwei Qian ,  Xun Chen

IPC: H04L29/06 ,  G06F21/62 ,  G06N20/00

CPC classification number: G06F21/6245 ,  G06N20/00

Abstract: A method includes obtaining, by an application executing on a processor of an electronic device, user data of a user, generating a representation of the user data, applying local differential privacy to the representation of the user data, to generate a transform of the representation of the user data, sending the transform of the representation of the user data, to a service provider via a network and receiving, from the service provider, via the network, service data based on the transform of the user data. The service data includes a user-specific output based on the transform of the user data. The application executes outside of a trusted execution environment (TEE) of the electronic device. The transform of the representation of the user data is generated in the TEE of the electronic device.

公开(公告)号：US11853793B2

公开(公告)日：2023-12-26

申请号：US17067532

申请日：2020-10-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Xun Chen ,  Jianwei Qian

IPC: G06F9/48 ,  G06F21/53 ,  G06F21/60 ,  G06N20/00 ,  G06N5/04 ,  G06N7/00 ,  G06F9/50 ,  G06F9/30 ,  G06F18/214

CPC classification number: G06F9/4881 ,  G06F9/30036 ,  G06F9/505 ,  G06F18/214 ,  G06F21/53 ,  G06F21/60 ,  G06N5/04 ,  G06N7/00 ,  G06N20/00

Abstract: An electronic device includes at least one transceiver, at least one memory, and at least one processor coupled to the at least one transceiver and the at least one memory. The at least one processor is configured to receive, via the at least one transceiver, an AI model in a trusted execution environment (TEE). The at least one processor is also configured to receive an inference request and input data from a source outside the TEE. The at least one processor is further configured to partition a calculation of an inference result between an internal calculation performed by processor resources within the TEE and an external calculation performed by processor resources outside the TEE. In addition, the at least one processor is configured to produce the inference result based on results of the internal calculation and the external calculation.

公开(公告)号：US20220269816A1

公开(公告)日：2022-08-25

申请号：US17375976

申请日：2021-07-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jianwei Qian ,  Xun Chen

IPC: G06F21/62 ,  G06N20/00

Abstract: A method includes obtaining, by an application executing on a processor of an electronic device, user data of a user, generating a representation of the user data, applying local differential privacy to the representation of the user data, to generate a transform of the representation of the user data, sending the transform of the representation of the user data, to a service provider via a network and receiving, from the service provider, via the network, service data based on the transform of the user data. The service data includes a user-specific output based on the transform of the user data. The application executes outside of a trusted execution environment (TEE) of the electronic device. The transform of the representation of the user data is generated in the TEE of the electronic device.