Patent · US Active

Computerized systems and methods for secure execution and offloading of computations between trusted and untrusted devices

US12306931B2 · kind B2 · utility

0Cited by

2References

20Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Betül Durak · Redmond, US
Stefan Gehrer · Erfurt, DE
Jorge Guajardo Merchan · Pittsburgh, US
Sven Trieflinger · Renningen, DE
Christian Zimmermann · Erlangen, DE

Key dates

Filing date	Jul 19, 2022
Grant date	May 20, 2025
Priority date	—
Expiry date	Oct 18, 2043

Classification

Technology area (CPC G)Physics
CPC primaryG06F2221/031
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Disclosed are systems and methods for a computerized framework that provides an improved, secure computational environment between trusted and untrusted devices (e.g., a Trusted Execution Environment (TEE) and graphics processing unit (GPU), respectively) for executing and offloading Convolutional Neural Network (CNN) computations and operations. The disclosed framework can operate to perform such secure offloading and processing not only during inference computations of the CNN, but also during training of the CNN. The disclosed framework operates to enable training and execution of CNN models, whereby the data used for such operations are held securely while they are in use, in transit (e.g., between the TEE and GPU) and while in storage.

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