公开(公告)号：WO2020167949A1

公开(公告)日：2020-08-20

申请号：PCT/US2020/017929

申请日：2020-02-12

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： KIM, Chung, Hwan ,  RHEE, Junghwan ,  JEE, Kangkook ,  LI, Zhichun ,  AHMAD, Adil ,  CHEN, Haifeng

IPC: G06F21/57 ,  G06F9/445 ,  G06F9/455

Abstract: Systems and methods for implementing a system architecture to support a trusted execution environment (TEE) with computational acceleration are provided. The method includes establishing a first trusted channel between a user application stored on an enclave and a graphics processing unit (GPU) driver loaded on a hypervisor (640). Establishing the first trusted channel includes leveraging page permissions in an extended page table (EPT) to isolate the first trusted channel between the enclave and the GPU driver in a physical memory of an operating system (OS). The method further includes establishing a second trusted channel between the GPU driver and a GPU device (650). The method also includes launching a unified TEE that includes the enclave and the hypervisor with execution of application code of the user application (660).

公开(公告)号：WO2020117551A1

公开(公告)日：2020-06-11

申请号：PCT/US2019/063184

申请日：2019-11-26

Applicant: NEC LABORATORIES AMERICA, INC.

Inventor： KIM, Chung, Hwan ,  RHEE, Junghwan ,  JEE, Kangkook ,  LI, Zhichun

IPC: G06F21/56 ,  G06F21/53

Abstract: A method for implementing confidential machine learning with program compartmentalization includes implementing a development stage to design an ML program (510), including annotating source code of the ML program to generate an ML program annotation, performing program analysis based on the development stage (520), including compiling the source code of the ML program based on the ML program annotation, inserting binary code based on the program analysis (530), including inserting run-time code into a confidential part of the ML program and a non-confidential part of the ML program, and generating an ML model by executing the ML program with the inserted binary code to protect the confidentiality of the ML model and the ML program from attack (542).