Novel Intrusion Detection Approach in Unbalanced Network Traffic Using Modified Random Forest Algorithm

The aim of this research is to improve how well the Random Forest Algorithm can find unusual activities in network security, especially when dealing with imbalanced data. The present work has involved two groups. Group 1 refers to a OSELM Algorithm, it cannot detect efficiently during network trafficking and Group 2 refers to Modified random forest detecting the real time data as normal or anomaly. The updated method is focusing on accuracy, completeness and overall performance measures. The modified random forest algorithm showcased exceptional performance in detecting intrusions within network traffic. With an average accuracy of 93%, the model outperformed the OSELM method. This study presents a novel intrusion detection approach tailored for unbalanced network traffic utilising a modified Random Forest Algorithm .