Algoritma Adasyn Dan Machine Learning XGBoost Untuk Sistem Deteksi Intrusi Pada Dataset Cicids 2017

Network security is a vital aspect in addressing the growing threat of cyberattacks. One of the main challenges in Intrusion Detection Systems (IDS) is the imbalance in data distribution between normal traffic and attack traffic. This study applies the ADASYN method to balance the training data and utilizes the XGBoost algorithm for classification using the CICIDS 2017 dataset. The model is evaluated using classification metrics such as accuracy, precision, recall, and f1-score. The results show that the model achieves an accuracy of 84.95%, recall (macro) of 90.70%, precision (macro) of 42.52%, and f1-score (macro) of 48.26%. The high recall indicates the model's ability to detect various types of attacks, including minority classes, although precision and f1-score vary across classes.