Research Article
Lightweight Intrusion Detection Model of the Internet of Things with Hybrid Cloud-Fog Computing
Table 5
Statistics of various types of samples in the training set and test set.
| Datasets | Sample types | Number of samples | Proportion of each type (%) |
| TON-IoT training set | Backdoor(0) | 18265 | 4.34 | DDoS(1) | 18265 | 4.34 | DoS(2) | 18264 | 4.34 | Injection(3) | 18265 | 4.34 | MITM(4) | 952 | 0.23 | Normal(5) | 273972 | 65.07 | Password(6) | 18265 | 4.34 | Ransomware(7) | 18265 | 4.34 | Scanning(8) | 18265 | 4.34 | XSS(9) | 18265 | 4.34 |
| TON-IoT test set | Backdoor(0) | 1735 | 4.34 | DDoS(1) | 1735 | 4.34 | DoS(2) | 1736 | 4.34 | Injection(3) | 1735 | 4.34 | MITM(4) | 91 | 0.23 | Normal(5) | 26028 | 65.07 | Password(6) | 1735 | 4.34 | Ransomware(7) | 1735 | 4.34 | Scanning(8) | 1735 | 4.34 | XSS(9) | 1735 | 4.34 |
| BoT-IoT training set | DoS(0) | 1716553 | 52.518 | DDoS(1) | 1470323 | 44.984 | Recon(2) | 425 | 0.013 | Normal(3) | 81151 | 2.483 | Theft(4) | 70 | 0.002 |
| BoT-IoT test set | DoS(0) | 210071 | 52.518 | DDoS(1) | 179937 | 44.984 | Recon(2) | 52 | 0.013 | Normal(3) | 9931 | 2.483 | Theft(4) | 9 | 0.002 |
|
|