Skripsi
DETEKSI SERANGAN DDOS DAN MITM PADA JARINGAN SMARTHOME DENGAN METODE MACHINE LEARNING XGBOOST
The rapid growth of Internet of Things (IoT) devices in smart home environments increases convenience but also introduces various network security threats, such as Distributed Denial of Service (DDoS) and Man in The Middle (MITM) attacks. This study aims to implement and evaluate the performance of the Extreme Gradient Boosting (XGBoost) algorithm in detecting DDoS and MITM attacks on IoT networks. The dataset used in this research is the COMNETS IoT dataset, which was collected from a controlled network topology with simulated attack scenarios. The preprocessing stage includes feature selection, label encoding, and data balancing using the Random Oversampling method. The XGBoost model was evaluated using a 30-fold cross-validation method to assess its robustness and generalization capability. The experimental results show that the XGBoost model with preprocessing achieved an accuracy of 93.9%, precision of 94.0%, recall of 93.0%, and an F1-score of 93.0%, indicating high performance in detecting DDoS and MITM attacks. Meanwhile, testing without preprocessing yielded perfect metrics (1.0) but indicated an overfitting condition. Therefore, it can be concluded that the preprocessing process significantly improves the generalization ability and stability of the XGBoost model in classifying network traffic on IoT environments. Keywords: XGBoost, IoT, DDoS, MITM, Attack Detection, Machine Learning.
| Inventory Code | Barcode | Call Number | Location | Status |
|---|---|---|---|---|
| 2507006345 | T185877 | T1858772025 | Central Library (Reference) | Available but not for loan - Not for Loan |