The Comparison of Machine Learning Methods for Email Spam Detection

User privacy has become a prominent issue in the digital age, especially with the advent of the Internet and social media. Technologies have opened up new opportunities and different ways for us to communicate. At the same time, they have also brought other avenues and methods for cyberattacks. Email attacks such as the mass sending of malicious messages, links, and phishing dominate among them. Therefore, in our scientific article, we dealt with the most common type of cyberattacks that occur via e-mail. Machine learning methods (ML) have been actively involved in malicious email detection. To find out which algorithm is more effective, we tested different supervised ML algorithms such as Random Forest, Support Vector Machine (SVM), Decision Tree, Naive Bayes, and K-Nearest Neighbors. And to work with real data, we used some datasets containing emails used in different phishing and bulk emails.