Hide/Show Apps

Detecting Turkish phishing attacks with machine learning classifiers

Turhanlar, Melih
Phishing Attacks are social engineering attacks that aim at stealing victim’s credit card numbers, credentials, and personal information by exploiting victim’s emotions, such as curiosity and fear. The attacker usually sends a webpage link in embodied in textual content. If the victim clicks the link, they usually connect to a mock webpage that imitates a real, institutional webpage. Filling the HTML forms in the mock webpage, the victim sends their credentials unwittingly to the attacker. In our day, phishing is a global issue. This study presents a framework for detecting phishing text in Turkish by running machine learning classifiers on an imbalanced phishing data set. The training dataset covers e-mails, SMS text and tweets. The results show that Logistic Regression Synthetic Minority Over-Sampling Technique achieves high performance, as indicated by Fmeasures, compared to a set of 32 machine learning models in our study.