DOI: https://doi.org/10.36719/2663-4619/116/42-45
Sayyad Ibrahimov
Azerbaijan Technical University
https://orcid.org/0009-0005-9224-6853
ibrahimovsayyad01@gmail.com
Application of Classical Text Classification Methods in Detecting Phishing Attacks
Abstract
Phishing attacks remain one of the most widespread and dangerous social engineering techniques in the field of cybersecurity. These attacks aim to deceive users and obtain their personal information. To prevent such threats, there is a growing need for effective and automated detection methods. This study investigates the application of classical text classification approaches in detecting phishing messages. Within the scope of the research, traditional classification models such as Naive Bayes, Support Vector Machines (SVM), Decision Tree, and Logistic Regression were evaluated for their ability to distinguish between phishing and non-phishing texts. Prior to the application of these models, feature extraction techniques (TF-IDF, n-grams, etc.) and data preprocessing steps were carried out. The performance of the models was analyzed based on evaluation metrics such as accuracy, precision, recall, and F1-score.
Keywords: phishing, cybersecurity, text classification, automated detection, artificial intelligence applications