Skip to main content

Table 8 Accuracy comparison using the UNSW-NB15 dataset [27]

From: A hybrid machine learning method for increasing the performance of network intrusion detection systems

Paper

Methods

Accuracy (%)

Nawir et al. [37]

Average One Dependence Estimator (AODE)

94.37

Bayesian Network (BN)

92.7

Kasongo and Sun [38]

Feature Norm. + XGBoost + DT

90.85

Feature Norm. + XGBoost + ANN

84.39

Feature Norm. + XGBoost + LR

77.64

Feature Norm. + XGBoost + KNN

84.46

Feature Norm. + XGBoost + SVM

60.89

Belouch et al. [39]

RepTree

88.95

Roy and Cheung [40]

BLSTM RNN

95.71

Viet et al. [41]

Deep Belief Network

99.45

Jing and Chen [42]

SVM Modeling

85.99

Proposed method

Hybrid Machine Learning Method

91.86