Building Auto-Encoder Intrusion Detection System based on random forest feature selection

Machine learning techniques have been widely used in intrusion detection for many years. However, these techniques are still suffer from lack of labeled dataset, heavy overhead and low accuracy. To improve classification accuracy and reduce training time, this paper proposes an effective deep learni...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers & security Jg. 95; S. 101851 - 15
Hauptverfasser: Li, XuKui, Chen, Wei, Zhang, Qianru, Wu, Lifa
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier Ltd 01.08.2020
Elsevier Sequoia S.A
Schlagworte:
Accuracy
Algorithms
Auto-Encoder
Classification
Coders
Deep learning
Feature selection
Intrusion
Intrusion detection systems
Machine learning
Network Intrusion Detection System
Network security
Training
Unsupervised clustering
Deep learning
Network security
Network Intrusion Detection System
Auto-Encoder
Unsupervised clustering
ISSN:0167-4048, 1872-6208
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Machine learning techniques have been widely used in intrusion detection for many years. However, these techniques are still suffer from lack of labeled dataset, heavy overhead and low accuracy. To improve classification accuracy and reduce training time, this paper proposes an effective deep learning method, namely AE-IDS (Auto-Encoder Intrusion Detection System) based on random forest algorithm. This method constructs the training set with feature selection and feature grouping. After training, the model can predict the results with auto-encoder, which greatly reduces the detection time and effectively improves the prediction accuracy. The experimental results show that the proposed method is superior to traditional machine learning based intrusion detection methods in terms of easy training, strong adaptability, and high detection accuracy.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-4048
1872-6208
DOI:10.1016/j.cose.2020.101851