Edge computing clone node recognition system based on machine learning

Edge computing is an important cornerstone for the construction of 5G networks, but with the development of Internet technology, the computer nodes are extremely vulnerable in attacks, especially clone attacks, causing casualties. The principle of clonal node attack is that the attacker captures the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural computing & applications Jg. 34; H. 12; S. 9289 - 9300
Hauptverfasser: Xiao, Xiang, Zhao, Ming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.06.2022
Springer Nature B.V
Schlagworte:
Accuracy
Algorithms
Artificial Intelligence
Casualties
Cloning
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Edge computing
Energy consumption
Image Processing and Computer Vision
Machine learning
Nodes
Paralysis
Probability and Statistics in Computer Science
Recognition
S.I.: AI-based Web Information Processing
Sensors
Servers
Special Issue on AI-based Web Information Processing
Edge Computing
Machine Learning
Clone Node
Node Recognition
ISSN:0941-0643, 1433-3058
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Edge computing is an important cornerstone for the construction of 5G networks, but with the development of Internet technology, the computer nodes are extremely vulnerable in attacks, especially clone attacks, causing casualties. The principle of clonal node attack is that the attacker captures the legitimate nodes in the network and obtains all their legitimate information, copies several nodes with the same ID and key information, and puts these clonal nodes in different locations in the network to attack the edge computing devices, resulting in network paralysis. How to quickly and efficiently identify clone nodes and isolate them becomes the key to prevent clone node attacks and improve the security of edge computing. In order to improve the degree of protection of edge computing and identify clonal nodes more quickly and accurately, based on edge computing of machine learning, this paper uses case analysis method, the literature analysis method, and other methods to collect data from the database, and uses parallel algorithm to build a model of clonal node recognition. The results show that the edge computing based on machine learning can greatly improve the efficiency of clonal node recognition, the recognition speed is more than 30% faster than the traditional edge computing, and the recognition accuracy reaches 0.852, which is about 50% higher than the traditional recognition. The results show that the edge computing clonal node method based on machine learning can improve the detection success rate of clonal nodes and reduce the energy consumption and transmission overhead of nodes, which is of great significance to the detection of clonal nodes.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-021-06283-1