Table 2 Attack recognition of the CREA-HDLMOA technique on the CIC-IDS2017 dataset.

From: Advancements in cyberthreat intelligence through resource exhaustion attack detection using hybrid deep learning with heuristic search algorithms

Class labels

\(\:\varvec{A}\varvec{c}\varvec{c}{\varvec{u}}_{\varvec{y}}\)

\(\:\varvec{P}\varvec{r}\varvec{e}{\varvec{c}}_{\varvec{n}}\)

\(\:\varvec{R}\varvec{e}\varvec{c}{\varvec{a}}_{\varvec{l}}\)

\(\:\varvec{F}{1}_{\varvec{S}\varvec{c}\varvec{o}\varvec{r}\varvec{e}}\)

\(\:\varvec{A}\varvec{U}{\varvec{C}}_{\varvec{S}\varvec{c}\varvec{o}\varvec{r}\varvec{e}}\)

TRASE (70%)

Benign

99.23

95.35

96.88

96.11

98.18

Bot

99.32

94.19

94.19

94.19

96.92

DDoS

99.16

95.05

96.28

95.66

97.88

DoS GoldenEye

98.98

95.52

94.08

94.79

96.80

DoS Hulk

99.23

95.35

96.69

96.01

98.10

DoS Slowhttptest

99.17

96.29

95.03

95.65

97.32

DoS Slowloris

99.29

95.87

97.00

96.43

98.27

FTP-PATATOR

99.05

94.50

95.93

95.21

97.66

PortScan

99.26

95.82

96.76

96.29

98.15

SSH-PATATOR

99.26

96.77

95.47

96.11

97.56

WebAttack BruteForce

99.24

92.77

91.54

92.15

95.59

WebAttack XSS

99.46

91.35

74.16

81.86

87.02

Average

99.22

94.90

93.67

94.21

96.62

TESSE (30%)

Benign

99.35

95.87

97.39

96.63

98.47

Bot

99.48

96.79

94.29

95.52

97.05

DDoS

99.13

95.40

96.01

95.70

97.75

DoS GoldenEye

99.19

96.17

95.18

95.67

97.39

DoS Hulk

99.25

95.53

97.25

96.38

98.37

DoS Slowhttptest

99.30

97.26

95.69

96.47

97.69

DoS Slowloris

99.21

94.62

97.12

95.85

98.27

FTP-PATATOR

99.12

94.67

96.28

95.47

97.85

PortScan

99.36

95.82

97.47

96.64

98.51

SSH-PATATOR

99.35

97.38

96.12

96.74

97.91

WebAttack BruteForce

99.57

95.74

95.31

95.53

97.55

WebAttack XSS

99.35

89.62

65.97

76.00

82.93

Average

99.31

95.41

93.67

94.38

96.65