公开(公告)号：US20240396711A1

公开(公告)日：2024-11-28

申请号：US18785435

申请日：2024-07-26

Applicant: Intel Corporation

Inventor： Akshay Kadam ,  Sivakumar B ,  Lawrence Booth, JR. ,  Niraj Gupta ,  Steven Tu ,  Ricardo Becker ,  Subba Mungara ,  Tuyet-Trang Piel ,  Mitul Shah ,  Raynald Lim ,  Mihai Bogdan Bucsa ,  Cliodhna Ni Scanaill ,  Roman Zubarev ,  Dmitry Budnikov ,  Lingyun Zhu ,  Yi Qian ,  Stewart Taylor

IPC: H04L9/06 ,  G06F9/455 ,  H04L9/08

Abstract: An accelerator includes a memory, a compute zone to receive an encrypted workload downloaded from a tenant application running in a virtual machine on a host computing system attached to the accelerator, and a processor subsystem to execute a cryptographic key exchange protocol with the tenant application to derive a session key for the compute zone and to program the session key into the compute zone. The compute zone is to decrypt the encrypted workload using the session key, receive an encrypted data stream from the tenant application, decrypt the encrypted data stream using the session key, and process the decrypted data stream by executing the workload to produce metadata.

公开(公告)号：US20220311594A1

公开(公告)日：2022-09-29

申请号：US17569488

申请日：2022-01-05

Applicant: Intel Corporation

Inventor： Akshay Kadam ,  Sivakumar B ,  Lawrence Booth, JR. ,  Niraj Gupta ,  Steven Tu ,  Ricardo Becker ,  Subba Mungara ,  Tuyet-Trang Piel ,  Mitul Shah ,  Raynald Lim ,  Mihai Bogdan Bucsa ,  Cliodhna Ni Scanaill ,  Roman Zubarev ,  Dmitry Budnikov ,  Lingyun Zhu ,  Yi Qian ,  Stewart Taylor

IPC: H04L9/06 ,  H04L9/08 ,  G06F9/455

Abstract: An accelerator includes a memory, a compute zone to receive an encrypted workload downloaded from a tenant application running in a virtual machine on a host computing system attached to the accelerator, and a processor subsystem to execute a cryptographic key exchange protocol with the tenant application to derive a session key for the compute zone and to program the session key into the compute zone. The compute zone is to decrypt the encrypted workload using the session key, receive an encrypted data stream from the tenant application, decrypt the encrypted data stream using the session key, and process the decrypted data stream by executing the workload to produce metadata.

公开(公告)号：US20240428048A1

公开(公告)日：2024-12-26

申请号：US18574786

申请日：2021-11-24

Applicant: Intel Corporation

Inventor： Wenjie Wang ,  Yi Zhang ,  Yi Qian ,  Wanglei Shen ,  Junjie Li ,  Lingyun Zhu

IPC: G06N3/04

Abstract: Technology providing in-memory neural network protection can include a memory to store a neural network, and a processor executing instructions to generate a neural network memory structure having a plurality of memory blocks in the memory, scatter the neural network among the plurality of memory blocks based on a randomized memory storage pattern, and reshuffle the neural network among the plurality of memory blocks based on a neural network memory access pattern. Scattering the neural network model can include dividing each layer of the neural network into a plurality of chunks, for each layer, selecting, for each chunk of the plurality of chunks, one of the plurality of memory blocks based on the randomized memory storage pattern, and storing each chunk in the respective selected memory block. The plurality of memory blocks can be organized into a groups of memory blocks and be divided between stack space and heap space.