Skip to main content

Table 9 Comparison results of other methods on UNSW-NB15 dataset

From: IGRF-RFE: a hybrid feature selection method for MLP-based network intrusion detection on UNSW-NB15 dataset

Work

Classifier

FS Method

No. of features

F1 score(%)

Accuracy(%)

Kasongo and Sun [25]

ANN

XGBoost

19

77.28

77.51

Roy and Singh [48]

MLP

IG

20

-

84.1

Kasongo and Sun [49]

FFDNN

WFEU

22

-

77.16

Eunice et al. [26]

DNN

DT

20

-

82.1

Moustafa and Slay [44]

ANN

-

42

-

81.34

Proposed method

MLP

IGRF-RFE

23

82.85

84.24