Social Networks Fake Profiles Detection Using Machine Learning Algorithms

Abstract

Fake profiles play an important role in advanced persisted threats and are also involved in other malicious activities. The present paper focuses on identifying fake profiles in social media. The approaches to identifying fake profiles in social media can be classified into the approaches aimed on analysing profiles data and individual accounts. Social networks fake profile creation is considered to cause more harm than any other form of cyber crime. This crime has to be detected even before the user is notified about the fake profile creation. Many algorithms and methods have been proposed for the detection of fake profiles in the literature. This paper sheds light on the role of fake identities in advanced persistent threats and covers the mentioned approaches of detecting fake social media profiles. In order to make a relevant prediction of fake or genuine profiles, we will assess the impact of three supervised machine learning algorithms: Random Forest (RF), Decision Tree (DT-J48), and Naive Bayes (NB).