SOCIAL ENGINEERING ATTACK DETECTION MODEL

Abstract

Social Engineering is a science of using social interaction as a means to persuade an individual or an organization to comply with a specific request from an attacker where the social interaction, the persuasion or the request involves a computer-related entity. In recent years social engineering attacks have emerged as a growing threat to cyber security, as attackers exploit human vulnerabilities to gain unauthorized access to systems and sensitive information. Ethiopia is no exception, facing an increasing number of such attacks targeted at individuals and institutions. As a result, multiple Rule-based and machine learning-based models have been developed to address this problem. This thesis proposes a tailored social engineering attack detection model primarily concerned with adapting and modifying SEADM version 2. The study makes use of survey data, literature review and analysis, and experimentation with real-life scenarios. The results show that the proposed model can be used as a tool by individuals to educate them about the most recent attack technique and to always be vigilant and on the lookout for social engineering attacks. And, has the potential to serve as a valuable tool for organizations and individuals seeking to enhance their cyber security defenses in Ethiopia and similar contexts. Finally, the study presents a tailored social engineering attack detection model (TSEADM) that has been tested using examples of generalized social engineering attacks, demonstrating that the TSEADM can withstand social engineering attacks.