Enhancing Intrusion Detection Systems Using Ensemble Machine Learning Techniques

Intrusion detection systems are an essential part of the current cybersecurity environment, and IDS devices are intended to scan the activity of the network and systems to identify possible improper actions or violations. IDSs work in analyzing the traffic of networks and the traffic of networks and the behavior of systems, distinguishing suspicious information and signs of violation of legal access. This capability is critical for protecting information systems’ characteristics, such as integrity, confidentiality, and availability. Useful data was collected from Kaggle data archives, and several base models such as K-Nearest Neighbor, Random Forest, Logistic Regression, and Decision Tree classifier will be used. Their predictions are combined using a Voting Classifier. The models are trained and evaluated based on accuracy, precision, recall, and F1-Score. Results show that the Voting classifier achieved an accuracy of 99.78%, with a precision of 99.67% and recall of 99.92% for intrusion detection. The Logistic Regression and K-Nearest Neighbor models achieved accuracies of 95.37% and 99.52%, respectively, while having a precision of 94.93% and 99.51%, respectively. The Decision Tree and Random Forest models achieved accuracies of 99.76% and 99.86%, respectively, while having a precision of 99.75% and 99.83%, respectively. These findings suggest ensemble techniques significantly enhance intrusion detection, making networks safer.