EXPLAINABLE AI FOR PHISHING DETECTION IN MULTILINGUAL AND LOW-RESOURCE CONTEXTS: A HUMAN-CENTERED CYBERSECURITY APPROACH

Abstract

Phishing attacks remain one of the most pervasive and effective forms of cybercrime worldwide. By exploiting human trust through deceptive emails, messages, and websites, attackers successfully steal sensitive information such as login credentials, financial data, and personal identities. Despite advances in technical defenses, phishing continues to evolve, becoming more sophisticated, personalized, and linguistically diverse.