Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An integrated detection method for edge side clone nodes based on backpropagation neural network

A backpropagation and neural network technology, applied in the field of integrated detection of clone nodes on the edge side, can solve the problems of increasing network transmission load and clone detection delay, increasing the computing load of the central network, etc.

Active Publication Date: 2019-06-07
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, it not only increases the computing load of the central network, but also increases the network transmission load and the delay of clone detection.

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
  • An integrated detection method for edge side clone nodes based on backpropagation neural network
  • An integrated detection method for edge side clone nodes based on backpropagation neural network
  • An integrated detection method for edge side clone nodes based on backpropagation neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0090] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following description.

[0091] Such as figure 1 As shown, the present invention is implemented in a network of terminals, nodes, and edge-side computing nodes with legitimate data sources. Clone node attack means that the attacker captures a legitimate data source node and obtains legal information such as its identity ID and key, and clones multiple clone nodes with the same ID at different physical locations in the network, thereby attacking the network. Way. The characteristic of the clone node is that the data sources with the same identity ID are located in different physical locations. The clone detection of the present invention is implemented on the computing nodes at the edge side, and clone attack detection is performed on the data source nodes. In th...

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 an integrated detection method of edge side clone nodes based on backpropagation neural network, comprising the following steps: S1. Edge side computing nodes collect data sets; S2. Use the data sets to train and test BPNN; S3. Wait New information packet; S4. Extract channel information from the information packet, store reference channel information, and calculate channel difference; S5. Accumulate the reputation of each node; S6. Input the reputation of each node into BPNN to determine whether there is a clone attack; S7 . If there is no cloning attack, update the reference channel information, and if there is a cloning attack, send a cloning attack alarm. The invention utilizes BPNN at the edge side nodes to perform integrated detection on the data source nodes, and simultaneously judges whether there is a clone attack in multiple nodes, improves the detection efficiency of the clone nodes, and reduces the network transmission load and the central network load. The present invention also reduces the influence of channel random noise and improves the accuracy of clone node detection by accumulating reputation and BPNN classification.

Description

technical field [0001] The present invention relates to the security protection of terminals or nodes, in particular to an integrated detection method for edge side clone nodes based on backpropagation neural network. Background technique [0002] The principle of the clone node attack is that the attacker captures the legal nodes in the network and obtains all their legal information, copies several nodes with the same ID and key information, and puts these clone nodes in different locations in the network to launch the attack . Because the cloned node has the same ID and key information as the legitimate node, it is difficult for the traditional cryptography-based authentication mechanism to detect the cloned node. How to quickly and efficiently detect clone nodes and isolate them has become the key to preventing clone node attacks. [0003] The principle of the clone detection scheme based on channel information is that if the same ID corresponds to different physical l...

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 Patents(China)
IPC IPC(8): H04L29/06
CPCH04L63/1408
Inventor 潘绯廖润发文红
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com