Table 40 Comparative evaluation with lightweight and reinforcement learning models (70% Training Data).
From: A hybrid deep learning model for detection and mitigation of DDoS attacks in VANETs
Model | Accuracy | Precision | F1-score | Sensitivity | Specificity | NPV | MCC | FPR | FNR | ROC-AUC |
|---|---|---|---|---|---|---|---|---|---|---|
MobileNetV2 | 0.95 | 0.93 | 0.95 | 0.96 | 0.93 | 0.96 | 0.9 | 0.07 | 0.04 | 0.975 |
SqueezeNet | 0.94 | 0.93 | 0.94 | 0.96 | 0.93 | 0.96 | 0.89 | 0.07 | 0.04 | 0.945 |
ShuffleNet | 0.94 | 0.93 | 0.94 | 0.96 | 0.93 | 0.96 | 0.9 | 0.07 | 0.04 | 0.945 |
DQN-based VANET Model | 0.95 | 0.93 | 0.95 | 0.96 | 0.93 | 0.96 | 0.91 | 0.07 | 0.04 | 0.96 |
PPO-Agent Model | 0.95 | 0.94 | 0.95 | 0.96 | 0.94 | 0.96 | 0.91 | 0.06 | 0.04 | 0.965 |
Proposed Fed-IDMF-VANET | 0.98 | 0.99 | 0.99 | 0.99 | 0.99 | 0.99 | 0.97 | 0.01 | 0.01 | 0.995 |
