Table 2 Public used datasets for IoT detection system.
From: Using machine learning algorithms to enhance IoT system security
Dataset | No. of features | No. of instances | Name of attacks | Separate train- test set |
|---|---|---|---|---|
BoTNet-IoT-L01 | 23 | 1,111,864 | UDP, Scan, Syn, Ack, TCP, UDP plain, Combo, and Junk | Yes |
NSL-KDD | 42 | 148,517 | DoS, Probe, R2L,and U2R | Yes |
KDD99 | 42 | 4,886,431 | DoS, Probe, R2L,and U2R | Yes |
UNSW-NB15 | 49 | 1,540,044 | DoS, Fuzzers, Backdoors, Worms, Reconnaissance, Analysis, Exploits, Generic, and Shellcode | Yes |
