Malicious url classification using machine learning algorithms and comparative analysis

Abstract

Exponential expansion in the application of the internet in each and every field has resulted in the escalation of data traffic over the internet. In the vastness of this data it has become important for engineers to classify the data as malicious and non-malicious so that different traffic can be treated differently. Rule-based and port-based classification exhibited a number of limitations which ultimately led to the steep decline in their usage to classify the internet traffic and gave rise to the machine learning techniques which are more promising and efficient. In this paper four popularly known machine learning classifiers: KNN, Naive Bayes, Decision Trees and Random forest have been implemented to classify the internet traffic based on whether the traffic is malicious or not and then compare their results on the basis of their accuracy score.