Published Paper Details:

Network analysts find it difficult to manually monitor traffic flows and spot breaches in large networks due to the astronomical volume of internet traffic and rising network complexity. Information security is significantly enhanced by intrusion detection systems (IDS). Recently, it has become more common to use Machine Learning (ML) approaches for intrusion-based detection. The network traffic generates a lot of data with irrelevant information, slowing down the detection process and deteriorating system performance. Elimination or selection is carried out prior to categorization to get around that flaw. This research presents a hybrid machine learning-based intrusion detection system that employs recursive feature removal. In order to adequately and effectively analyze network traffic for intrusions, Support Vector Machine (SVM) and Decision Tree (DT) machine learning models are combined into hybrid machine learning model. Furthermore, a multi-class classifier was built to classify not only malicious or benign traffic but also to extend labels upon the malicious data. In order to improve the performance, this system identifies the features which are irrelevant and eliminated it. The feature selection is achieved by using Recursive Feature elimination method. Experiments show improved performance in network intrusion detection.