Network Intrusion Detection Method Based on FCWGAN and BiLSTM

Table 12

Comparison of classification algorithms on UNSW-NB15 dataset.

Algorithm	Evaluation metrics
	Accuracy	Precision	Recall	F1-score	Time (s)
FCWGAN-RF	81.00 ± 0.37	81.94 ± 0.33	80.97 ± 0.31	81.45 ± 0.32	1
FCWGAN-DNN	83.44 ± 0.31	84.12 ± 0.33	83.40 ± 0.27	83.76 ± 0.30	2
FCWGAN-LSTM	84.98 ± 0.30	85.44 ± 0.29	84.67 ± 0.25	85.05 ± 0.28	3
Model in this paper	85.59 ± 0.27	86.11 ± 0.21	85.57 ± 0.24	85.84 ± 0.22	4