A New Network Security Model Based on Machine Learning

Rough set classifier or SVM (Support Vector Machine) classifier is a typical machine learning model. The Rough set classifier and SVM classifier are used to classify nodes as trust nodes, strange nodes and malicious nodes. We use the Rough set classifier to replace the method by settings of the thre...

Full description

Saved in:
Bibliographic Details
Main Authors: Hai-Sheng Wang, Xiao-Lin Gui
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Computational efficiency
Educational institutions
Peer to peer computing
Rough set
Security
Security model
Simulation experiment
Support vector machines
SVM classifier
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rough set classifier or SVM (Support Vector Machine) classifier is a typical machine learning model. The Rough set classifier and SVM classifier are used to classify nodes as trust nodes, strange nodes and malicious nodes. We use the Rough set classifier to replace the method by settings of the threshold. The innovation of the article is to improve the computation accuracy and the efficiency of the classification computation by using Rough set combined with SVM classifier. In the cases where according to the value of an attribute or the values of two attributes the corresponding classification result can be determined, we use the Rough set classifier. In other cases, we use SVM classifier. Compared with existing security models, experiment results indicate that the model can obtain the higher examination rate of malicious nodes and the higher transaction success rate.
DOI:10.1109/ICCECT.2012.28