Table 35 Impact of Overfitting Mitigation on VANET-DDoSNet++ Performance (70% Training Data).
From: A hybrid deep learning model for detection and mitigation of DDoS attacks in VANETs
Metric | Before mitigation | After mitigation |
|---|---|---|
Training accuracy | 99.8% | 93.9% |
Testing accuracy | 88.5% | 92.7% |
Validation accuracy | 89.2% | 97.71% |
Precision | 90.1% | 96.8% |
Recall | 88.7% | 95.5% |
F1-Score | 89.4% | 96.1% |
AUC-ROC | 0.91 | 0.98 |
Overfitting Gap | 11.3% | 1.2% |
