Open AccessResearch on Network APT Attack Intrusion Detection Technology Based on Machine Learning Algorithm
Author(s) -
Qingyu Meng,
Yang Yang,
Fengzhi Wu,
Xiang Chen,
Xiaoming Chen
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/799/1/012029
Subject(s) - intrusion detection system , computer science , network security , anomaly based intrusion detection system , intrusion , support vector machine , attack model , algorithm , attack patterns , classifier (uml) , data mining , machine learning , artificial intelligence , computer security , geochemistry , geology
The attack frequency of network advanced persistent threat (APT) is more and more higher, which seriously endangers the network security. In order to obtain high accuracy of network APT attack intrusion detection results, aiming at the limitations of current network APT attack intrusion detection model, a network APT attack intrusion detection model based on machine learning algorithm is proposed. A “one-to-one” network APT attack intrusion detection classifier is built through a neutral and excellent support vector mechanism of machine learning algorithm, and the current standard network APT attack intrusion detection database is adopted to verify the validity of the model. The accuracy of network APT attack intrusion detection is over 95%, and the detection error is far lower than the actual application range. It can be used in the actual network security management.