Network Intrusion Detection Method Based on FCWGAN and BiLSTM

Table 10

Comparison of data enhancement algorithms on UNSW-NB15 dataset.

Algorithm	Evaluation metrics
	Accuracy	Precision	Recall	F1-score	Time (s)
ROS-BiLSTM	81.70 ± 0.43	79.32 ± 0.47	80.49 ± 0.41	79.90 ± 0.44	6
ADASYN-BiLSTM	83.65 ± 0.37	84.11 ± 0.40	82.14 ± 0.35	83.12 ± 0.37	6
SMOTE-BiLSTM	83.66 ± 0.31	84.28 ± 0.34	81.24 ± 0.27	82.73 ± 0.30	5
WGAN-BiLSTM	81.49 ± 0.30	84.71 ± 0.24	82.51 ± 0.28	83.60 ± 0.26	8
Model in this paper	85.59 ± 0.27	86.11 ± 0.21	85.57 ± 0.24	85.84 ± 0.22	4