Security and Communication Networks

Research Article

A GAN and Feature Selection-Based Oversampling Technique for Intrusion Detection

Table 5

Subsets of features selected based on ANOVA.
DatasetSelected featuresQuantity
NSL-KDDprotocol_type, flag, logged_in, count, serror_rate, srv_serror_rate, rerror_rate, srv_rerror_rate, same_srv_rate, dst_host_count, dst_host_srv_count, dst_host_same_srv_rate, dst_host_serror_rate, dst_host_srv_serror_rate, dst_host_rerror_rate, dst_host_srv_rerror_rate16
UNSW-NB15Proto, dttl, dloss, sinpkt, swin, stcpb, dtcpb, dwin, dmean, ct_state_ttl, ct_dst_ltm, ct_src_dport_ltm, is_sm_ips_ports13
CICIDS-2017Destination Port, Flow Duration, Fwd Packet Length Max, Fwd Packet Length Min, Fwd Packet Length Mean, Bwd Packet Length Max, Bwd Packet Length Min, Bwd Packet Length Mean, Bwd Packet Length Std, Flow Packets/s, Flow IAT Mean, Flow IAT Std, Flow IAT Max, Fwd IAT Total, Fwd IAT Mean, Fwd IAT Std, Fwd IAT Max, Bwd IAT Std, Bwd IAT Max, Fwd PSH Flags, Min Packet Length, Max Packet Length, Packet Length Mean, Packet Length Std, Packet Length Variance, FIN Flag Count, SYN Flag Count, PSH Flag Count, ACK Flag Count, URG Flag Count, Down/Up Ratio, Average Packet Size, Avg Fwd Segment Size, Avg Bwd Segment Size, Init_Win_bytes_backward, Idle Mean, Idle Std, Idle Max, Idle Min39