EFS-DNN: An Ensemble Feature Selection-Based Deep Learning Approach to Network Intrusion Detection System

Table 4

Statistics of UNSW-NB15.

Attack type	Train		Test
	Size	Distribution (%)	Size	Distribution (%)
Normal	56000	31.94	37000	44.94
Generic	40000	22.81	18871	22.92
Exploits	33393	19.04	11132	13.52
Fuzzers	18184	10.37	6062	7.36
DoS	12264	6.99	4089	4.97
Reconnaissance	10491	5.98	3496	4.25
Analysis	2000	1.14	677	0.82
Backdoor	1746	1.00	583	0.71
Shellcode	1133	0.65	378	0.46
Worms	130	0.07	44	0.05