Uncertainty-Aware Zero-Day Botnet Detection for IoT Networks with Real-World Edge Deployment on Resource-Constrained Hardware
This study evaluates a calibrated two-tier detection pipeline combining an XGBoost gradient-boosted tree classifier for known-class prediction with a Monte Carlo dropout multilayer perceptron (MLP) as an independent uncertainty estimator, under conditions closer to real deployment than most prior evaluations.
Cinmoy Purkaystha, Y. Gandhi, Prashant Kumar
· Italian National Conference... · 0 citations