Publication: Anomaly-Based Network Intrusion Detection System through Feature Selection and Hybrid Machine Learning Technique
1
0
Issued Date
2019
Resource Type
File Type
application/pdf
ISSN
21570981
Other identifier(s)
2-s2.0-85061932044
Rights Holder(s)
มหาวิทยาลัยศรีนครินทรวิโรฒ
Bibliographic Citation
International Conference on ICT and Knowledge Engineering. Vol 2018-November, (2019), p.64-69
Suggested Citation
Pattawaro A., Polprasert C. Anomaly-Based Network Intrusion Detection System through Feature Selection and Hybrid Machine Learning Technique. International Conference on ICT and Knowledge Engineering. Vol 2018-November, (2019), p.64-69. doi:10.1109/ICTKE.2018.8612331 Retrieved from: https://hdl.handle.net/20.500.14740/5502
Author(s)
Abstract
In this paper, we propose an anomaly-based network intrusion detection system based on a combination of feature selection, K-Means clustering and XGBoost classification model. We test the performance of our proposed system over NSL-KDD dataset using KDDTest + dataset. A feature selection method based on attribute ratio (AR) [14] is applied to construct a reduced feature subset of NSL-KDD dataset. After applying K-Means clustering, hyperparameter tuning of each classification model corresponding to each cluster is implemented. Using only 2 clusters, our proposed model obtains accuracy equal to 84.41% with detection rate equal to 86.36% and false alarm rate equal to 18.20% for KDDTest + dataset. The performance of our proposed model outperforms those obtained using the recurrent neural network (RNN)-based deep neural network and other tree-based classifiers. In addition, due to feature selection, our proposed model employs only 75 out of 122 features (61.47%) to achieve this level of performance comparable to those using full number of features to train the model. © 2018 IEEE.
Subject(s)
Computer crime
Deep neural networks
Intrusion detection
K-means clustering
Knowledge engineering
Network security
Recurrent neural networks
Statistical tests
Classification models
False alarm rate
Feature selection methods
Hybrid clustering
Hybrid machine learning
Network intrusion detection systems
NSL-KDD
Recurrent neural network (RNN)
Feature extraction
Deep neural networks
Intrusion detection
K-means clustering
Knowledge engineering
Network security
Recurrent neural networks
Statistical tests
Classification models
False alarm rate
Feature selection methods
Hybrid clustering
Hybrid machine learning
Network intrusion detection systems
NSL-KDD
Recurrent neural network (RNN)
Feature extraction