A novel approach for phishing URLs detection using lexical based machine learning in a real-time environment

In recent times, we can see a massive increase in the number of devices that are being connected to the internet. These devices include but are not limited to smartphones, IoT, and cloud networks. In comparison to other possible cyber-attacks, these days, hackers are targeting these devices with phishing attacks since it exploits human vulnerabilities rather than system vulnerabilities. In a phishing attack, an online user is deceived by a seemingly trusted entity to give their personal data, i.e., login credentials or credit card details. When this private information is leaked to the hackers, this information becomes the source of other sophisticated attacks. In recent times many researchers have proposed the machine learning-based approach to solve phishing attacks; however, they have used a large number of features to develop reliable phishing detection techniques. A large number of features requires large processing powers to detect phishing, which makes it very much unsuitable for resource constrained devices. To address this issue, we have developed a phishing detection approach that only needs nine lexical features for effectively detecting phishing attacks. We used ISCXURL-2016 dataset for our experimental purpose, where 11964 instances of legitimate and phishing URLs are used. We have tested our approach against different machine learning classifiers and have obtained the highest accuracy of 99.57% with the Random forest algorithm.