Research Article
Flow Correlation Degree Optimization Driven Random Forest for Detecting DDoS Attacks in Cloud Computing
Table 2
Comparison results of four algorithm detection evaluation criteria with changing numbers of attack training samples.
| ā | Sample numbers | 30 | 60 | 90 | 120 |
| GAORF (%) | accuracy | 100 | 100 | 100 | 100 | MR | 0 | 0 | 0 | 0 | FR | 0 | 0 | 0 | 0 | nu-SVM (%) | accuracy | 90.0 | 98.1 | 99.05 | 100 | MR | 0 | 0 | 0 | 0 | FR | 19.09 | 3.63 | 1.82 | 0 | C-SVM (%) | accuracy | 97.14 | 100 | 100 | 100 | MR | 6.0 | 0 | 0 | 0 | FR | 0 | 0 | 0 | 0 | one-class-SVM (%) | accuracy | 65.0 | 65.0 | 65.0 | 65.0 | MR | 0 | 0 | 0 | 0 | FR | 70.0 | 70.0 | 70.0 | 70.0 |
|
|