Comparative Study of Intrusion Detection Systems: Machine Learning Vs Deep Learning Approaches

Intrusion Detection Systems (IDS) play a crucial role in safeguarding modern network infrastructuresby identifying malicious activities and preventing potential security breaches. This study presents acomparative analysis of machine learning algorithms—Decision Trees, Support Vector Machines(SVM), Random Forest, and K-Nearest Neighbors (KNN)—to evaluate their effectiveness in intrusiondetection. Using standard datasets such as KDD Cup 99 and NSL-KDD, each algorithm was testedbased on accuracy, precision, recall, and F1-score. The results show that Random Forest outperformsother models with an accuracy of 95.3% and an F1-score of 94.2%, followed by SVM with a strongperformance in high-dimensional data classification. Decision Trees demonstrated a reasonable balancebetween interpretability and performance, while KNN struggled with scalability and high-dimensionalnetwork traffic. These findings highlight the importance of selecting the appropriate machine learningtechnique for IDS, based on the specific requirements of the network environment and the complexity ofpotential threats.