Enhancing Cybersecurity with Random Forest: Efficient Detection of Cyberattacks

Abstract

The rapid increase in the number of cyberattacks in the digital age has reduced the effectiveness of conventional cybersecurity systems. Traditional methods of cybersecurity face considerable difficulty when detecting new, sophisticated attacks and advanced exploitation techniques swiftly. This research addresses critical cybersecurity concerns by developing an AI-driven Intrusion Detection System (IDS), which employs Random Forest (RF) algorithms to detect cyberattacks efficiently. The evaluation of the model was conducted using three publicly available datasets: CICIDS2017 (692,703 records), NSL-KDD (148,517 records), and UNSW-NB15 (257,673 records) with various attack backgrounds and network configurations. A set of evaluation metrics, including accuracy, precision, recall, and F1-score, was employed to assess the performance of the cyberattack detection prototype. Across the three datasets, the model attained an average accuracy of 99.85%, precision of 99.83%, recall of 99.91%, and an F1-score of 99.87%, while maintaining low error rates, with an average false positive rate of 0.25% and a false negative rate of 0.10%. The results indicate that Random Forest is an effective solution for cyberattack detection in data-driven environments. The model was developed with lightweight and easy-to-deploy criteria, but the evaluation reported in this study was done under benchmark test conditions. This work improves the effectiveness of machine learning-based intrusion detection systems and serves as a stepping stone for future research on operational and real-time deployment of machine learning-based intrusion detection systems.