Skip to main content

Table 7 Evaluation metrics of multi-classification of UNSW-NB15

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

 

Precision

Recall

F1 Score

FPR

Accuracy

DoS

0.3612

0.0655

0.1109

0.0062

84.24%

Expl.

0.5980

0.9222

0.7255

0.0993

Fuzz.

0.4930

0.3698

0.4226

0.0309

Gene.

0.9982

0.9662

0.9820

0.0005

Norm.

0.9388

0.9236

0.9311

0.0510

Recon.

0.7807

0.7883

0.7845

0.0100

Weighted

Avg.

0.8360

0.8424

0.8285

0.0403