A Machine Learning-Based Intrusion Detection System for Network Security Enhancement

Cybersecurity threats are increasing rapidly due to the growth of internet-connected devices and the sophistication of attack methods. Traditional intrusion detection systems (IDS) rely on signature- based approaches that struggle to detect unknown or evolving attacks. This paper proposes a machine learning-based intrusion detection system designed to classify and detect malicious network traffic effectively. Using benchmark datasets such as IDSAI and Bot-IoT, multiple algorithms were evaluated for classification accuracy, precision, recall, and F1-score. The proposed system demonstrates improved detection rates for denial-of- service (DoS), brute force, and botnet-related intrusions compared to traditional methods. The results indicate that machine learning can significantly enhance intrusion detection, offering a robust and adaptive solution for modern cybersecurity challenges.