Malicious URLs Detection Using Decision Tree Classifiers and Majority Voting Technique

摘要

Researchers all over the world have provided significant and effectivesolutions to detect malicious URLs. Still due to the ever changing nature of cyberattacks, there are many open issues. In this paper, we have provided an effectivehybrid methodology with new features to deal with this problem. To evaluate ourapproach, we have used state-of-the-arts supervised decision tree learningclassifications models. We have performed our experiments on the balanceddataset. The experimental results show that, by inclusion of new features all thedecision tree learning classifiers work well on our labeled dataset, achieving 98-99% detection accuracy with very low False Positive Rate (FPR) and FalseNegative Rate (FNR). Also we have achieved 99.29% detection accuracy with verylow FPR and FNR using majority voting technique, which is better than the wellknown anti-virus and anti-malware solutions.