Feedback neural network trusted execution method and device

A technology of feedback neural network and execution device, applied in the field of deep learning, can solve the problems of less research on the safety and reliability of feedback neural network, and achieve the effect of ensuring reliable operation

Pending Publication Date: 2020-12-29
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the safety and reliability of feedback neural network execution are rarely studied. Based on the characteristics of feedback neural network, this paper studies various security problems faced by feedback neural network, and proposes a method of trusted execution of feedback neural network. and devices

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Feedback neural network trusted execution method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings. figure 1 It is the overall flowchart of the method involved in the present invention.

[0033] Step 1: Start the trust chain construction on the platform where the feedback neural network is located

[0034] Before the CPU and GPU are started, the active immune chip actively measures: the feedback neural network-specific hardware configuration and the feedback neural network-specific firmware of the platform where the feedback neural network is located, and compares the measurement results with the standard values ​​stored in the active immune chip. Determine if the Feedback Neural Network specific hardware configuration and Feedback Neural Network specific firmware are complete.

[0035] After the firmware startup of the active immune chip, before the OSLoader code is loaded, the OSLoader code of the platform where the feedback neural network ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a feedback neural network trusted execution method and device, and relates to the field of deep learning and the field of information security. The system comprises a calculation component and a protection component which are parallel, and the calculation component is used for completing calculation tasks such as a feedforward mechanism module and a feedback mechanism module; the protection component is used for carrying out active measurement and active control on the calculation component through an active immune chip according to a dynamic autonomous trusted strategy; a security isolation mechanism is arranged between the computing component and the protection component, and interaction is carried out through a special access channel; the method is based on the trusted computing 3.0 technology, and the safety of the feedback neural network is improved. By performing credibility verification on each key link of feedback neural execution, the safety and credibility of feedback neural network execution are ensured.

Description

technical field [0001] The invention relates to the fields of deep learning and information security, and its main feature is that if a suitable credible execution scheme is constructed for the feedback neural network. Background technique [0002] Feedback neural network, that is, neural network with feedback mechanism, mainly includes recurrent neural network, memory neural network, Hopfield neural network and other neural networks, and is an important part of artificial intelligence algorithms. However, the safety and reliability of feedback neural network execution are rarely studied. Based on the characteristics of feedback neural network, this paper studies various security problems faced by feedback neural network, and proposes a method of trusted execution of feedback neural network. and devices. Contents of the invention [0003] The purpose of the present invention is to propose a trusted execution method and device for a feedback neural network based on Trusted...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06F21/52
CPCG06N3/084G06F21/52G06N3/044
Inventor 彭晋宁振虎
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap