Network Intrusion Detection Method Based on FCWGAN and BiLSTM

Table 14

Comparison of multiclassification on UNSW-NB15 dataset.

Algorithm	Evaluation metrics
	Accuracy	Precision	Recall	F1-score	Time (s)
CNN-BiLSTM	82.08 ± 0.43	82.68 ± 0.43	80.00 ± 0.37	81.32 ± 0.40	10
SSAE-LSTM	82.31 ± 0.45	83.65 ± 0.44	81.94 ± 0.36	82.78 ± 0.41	7
CWGAN-DNN	82.61 ± 0.37	82.95 ± 0.41	82.11 ± 0.33	82.53 ± 0.38	14
AE-CGAN-RF	81.24 ± 0.39	83.47 ± 0.40	80.31 ± 0.35	81.86 ± 0.38	13
Model in this paper	85.59 ± 0.27	86.11 ± 0.21	85.57 ± 0.24	85.84 ± 0.22	4