A Comparative Study on Machine Learning Techniques in Analyzing Cybersecurity Network Data

The day by day increasing occurrences of cyber attacks led to the development of highly accurate and effective Intrusion Detection Systems (IDS). This paper presents a comparative study on the effectiveness of various Machine Learning (ML) techniques in analyzing complex cybersecurity network data. The primary objective is to evaluate and compare the performance of popular classifiers, including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Naïve Bayes (NB), using a public dataset (e.g., CIC-IDS2017). The performance is measured with key metrics such as detection accuracy, Scalability and Training time. The results indicate that ensemble methods, particularly Random Forest, consistently outperform single-model classifiers in terms of overall accuracy and robustness. This research finding provides valuable guidance for researchers in selecting the optimal ML architecture to construct a reliable and scalable network defense mechanism against evolving cyber-attacks.