Table 6 Performance metrics of the proposed model on the CICIDS2017 dataset.

From: A hybrid intrusion detection model based on dynamic spatial-temporal graph neural network in in-vehicle networks

Attack type

Accuracy (%)

Precision (%)

Recall (%)

F1-score (%)

FPR (%)

Benign

99.99

99.99

1.00

99.99

0.02

Bot

1.00

1.00

1.00

1.00

0.00

DDos

99.99

1.00

99.81

99.90

0.00

Dos GoldenEye

1.00

1.00

1.00

1.00

0.00

Dos Hulk

99.99

99.89

1.00

99.94

0.03

Dos Slowhttptest

99.99

99.76

1.00

99.88

0.00

Dos Slowloris

99.99

1.00

99.76

99.88

0.00

FTP-patator

99.99

1.00

99.74

99.87

0.00

Heartbleed

99.99

1.00

97.56

98.77

0.00

Infiltration

1.00

1.00

1.00

1.00

0.01

Portcan

1.00

1.00

1.00

1.00

0.01

SSH-patator

99.99

99.74

1.00

99.87

0.01

Brute force

99.93

99.74

97.49

98.61

0.00

SQL injection

1.00

1.00

1.00

1.00

0.00

XSS

99.93

99.49

99.74

99.61

0.00