MACHINE LEARNING MODEL FOR ANOMALY-BASED INTRUSION DETECTION USING RANDOM FOREST CLASSIFIER
Ebiesuwa Seun, Nwachukwu Victor, Falana Taye, A Adepoju-Bello Aderonke, Dipo Tepede, Adio Adesina · Indian Journal of Computer Science and Engineering · 2024
The dynamic nature of cyber threats creates a gap between the detection capabilities of existing anomaly-based Intrusion Detection System (IDS) and their inability to quickly adjust to new threat vectors.One of the most important challenges is achieving high accuracy in detecting anomalous signatures while mitigating false alarms.This proposed approach seeks to enhance the model's ability to recognize abnormal patterns in network behaviour by fusing the power of Random Forest with anomaly detection capabilities.The ensemble technique helps tackle the ever-changing nature of cyber threats.The model exhibits robustness to various intrusion scenarios and achieves excellent accuracy by combining predictions from different decision trees.By adding Random Forest to the ensemble, the protection system against changing cyber threats becomes more resilient and adaptable.Model evaluation was carried out using the NSL-KDD dataset, showcasing its effectiveness in detecting anomalies within network traffic.The results emphasize the model's potential to protect digital ecosystems from advanced cyberattacks by highlighting its capacity to identify minute departures from typical behaviour.