R. Alizadeh

A Five-Run Comparison of Lightweight Machine Learning Models for IoT Intrusion Detection

IoT intrusion-detection models are useful only if they detect attacks without becoming too costly to run. We compared Logistic Regression, Decision Tree, Random Forest, and XGBoost on binary CICIoT2023 intrusion detection using a cleaned file with 21,005,260 rows and 37 numeric features. The main experiment used five a...