Patent · US Active

Method, device, and program product for inference

US12413563B2 · kind B2 · utility

0Cited by

3References

20Claims

0Family size

Assignee

Dell Products L.P. · US

Inventors

Tianxiang Chen · Shanghai, CN
Jinpeng Liu · Shanghai, CN
Wenqing Peng · Shanghai, CN
Zhen Jia · Shanghai, CN

Key dates

Filing date	Feb 7, 2024
Grant date	Sep 9, 2025
Priority date	—
Expiry date	May 19, 2044

Classification

Technology area (CPC H)Electricity
CPC primaryH04L63/045
WIPO fieldDigital communication
WIPO sectorElectrical engineering

Abstract

Embodiments of the present disclosure relate to a method, a device, and a computer program product for inference. The method includes determining, for a layer in a neural network model, whether a weight matrix of the layer is an irreversible target matrix. The method further includes partitioning, in response to determining that the weight matrix of the layer is the target matrix, the neural network model into a first part and a second part, wherein the first part includes the layer and a previous layer before the layer and is deployed inside a security space, and the second part includes a subsequent layer after the layer and is deployed outside the security space. The method further includes acquiring an inference result by using the partitioned neural network model based on encrypted inference data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.