Table 5 Intrusion detection outcome of the OMHSA-IDPRGO model on the ToN-IoT dataset.

From: Advances in IoT networks using privacy-preserving techniques with optimized multi-head self-attention model for intelligent threat detection based on plant rhizome growth optimization

Class labels

\(Accu_{y}\)

\(\Pr ec_{n}\)

\({\text{Re}} ca_{l}\)

\(F1_{Score}\)

\(G_{Measure}\)

TRPHE (70%)

 Normal

98.07

98.01

99.06

98.53

98.53

 MiTM

99.76

72.46

21.28

32.89

39.27

 DoS

99.47

94.26

94.19

94.23

94.23

 DDoS

99.24

92.65

92.07

92.36

92.36

 Password

99.24

92.90

91.67

92.28

92.28

 Injection

99.17

91.89

91.29

91.58

91.59

 XSS

99.12

92.74

89.49

91.09

91.10

 Ransomware

99.26

93.33

91.43

92.37

92.38

 Backdoor

99.30

93.85

91.97

92.90

92.90

 Average

99.18

91.34

84.72

86.47

87.18

TSPHE (30%)

 Normal

98.07

97.93

99.14

98.53

98.53

 MiTM

99.76

75.00

23.76

36.09

42.22

 DoS

99.45

94.05

93.70

93.87

93.87

 DDoS

99.26

93.09

92.11

92.60

92.60

 Password

99.15

93.47

89.78

91.59

91.61

 Injection

99.17

91.95

90.78

91.36

91.36

 XSS

99.14

92.03

90.19

91.10

91.11

 Ransomware

99.26

93.48

91.97

92.72

92.72

 Backdoor

99.24

93.32

91.47

92.39

92.39

 Average

99.17

91.59

84.77

86.70

87.38