Identifying Generic Features for Malicious URL Detection System

Malicious URLs pose serious cybersecurity threats to the Internet users. It is critical to detect malicious URLs so that they could be blocked from user access. Several techniques have been proposed to differentiate malicious URLs from benign ones. However, the goal of our work is to find the list of substantial features that can be used to classify most of the malicious URLs. In this paper, we select the most significant lexical features from different datasets using Chi-Square and ANOVA F-value. Later, we apply a voting classifier that combines several machine learning algorithms on those selected features.