Intrusion Detection System(IDS) Analysis Using ML
The accuracy of four different machine learning models has been used to the NSL-KDD dataset to provide enhanced accuracy and outperform some other conventional classifiers for attack classifications and indicate that this suggested approach can provide a reduced false alarm rate while keeping a high diagnosis rate.
Abstract
It is seen how intrusion detection systems in networks have gained notoriety and grown to be a significant factor in the area of analysis as a result of the digital revolution and the growth of its operation. The Intrusion Detection System classifies the attack as hostile or conventional based on the users' behavior. A Network Intrusion Detection System (NIDS) handles congested network data. Despite being unorganized, it has the ability to handle challenging situations. The previous study documented many intrusion detection systems, all of which had varying degrees of accuracy. Although no model can accurately detect or foresee a cyberattack. Therefore, creating an effective and reliable intrusion detection model is crucial. In this study, the accuracy of four different machine learning models has been used to the NSL-KDD dataset to provide us enhanced accuracy and outperform some other conventional classifiers for attack classifications. This study and evaluation of the model’s performance used the NSL-KDD dataset. The final results indicate that this suggested approach can provide a reduced false alarm rate while keeping a high diagnosis rate.