Intrusion-Detection-System-Using-Machine-Learning and Intrusion-Detection-System-Using-CNN-and-Transfer-Learning
These are complementary approaches to the same problem—one uses traditional ML algorithms (decision trees, random forests, XGBoost) while the other uses deep learning (CNN and transfer learning)—so practitioners might evaluate both or combine their predictions for ensemble-based intrusion detection.
About Intrusion-Detection-System-Using-Machine-Learning
Western-OC2-Lab/Intrusion-Detection-System-Using-Machine-Learning
Code for IDS-ML: intrusion detection system development using machine learning algorithms (Decision tree, random forest, extra trees, XGBoost, stacking, k-means, Bayesian optimization..)
Implements three distinct IDS architectures: a tree-based supervised learner, a multi-tiered hybrid system combining signature-based and anomaly-based detection with k-means clustering for zero-day attacks, and LCCDE—a decision ensemble selecting class-specific leader models from XGBoost/LightGBM/CatBoost. Targets vehicular networks (CAN-bus, V2X) and general IoT environments, evaluated on Car-Hacking and CICIDS2017 datasets. Integrates Bayesian optimization (TPE and Gaussian Process variants) for hyperparameter tuning across supervised and unsupervised learners.
About Intrusion-Detection-System-Using-CNN-and-Transfer-Learning
Western-OC2-Lab/Intrusion-Detection-System-Using-CNN-and-Transfer-Learning
Code for intrusion detection system (IDS) development using CNN models and transfer learning
Scores updated daily from GitHub, PyPI, and npm data. How scores work