Table 4 Comparative performance analysis of the proposed method with the existing literature of a similar nature.
From: Orchestrating machine learning models in a swarm architecture for IoT inline malware detection
Study | Technique | Algorithms | Accuracy | ZDAD | AT | HA |
|---|---|---|---|---|---|---|
Bi-LSTM | Neural network | 93.8% | \(\checkmark\) | \(\times\) | \(\times\) | |
Two-Tier classification | SVM, NB, MLP, J48, ZeroR | 84.82% | \(\checkmark\) | \(\times\) | \(\checkmark\) | |
Fraudulent traffic detection | GAN, LSTM | 97.0% | \(\times\) | \(\times\) | \(\times\) | |
Proposed | SIML | DT, RF, GB | 93.7% | \(\checkmark\) | \(\checkmark\) | \(\checkmark\) |
