Malicious accounts: Dark of the social networks

Over the last few years, online social networks (OSNs), such as Facebook, Twitter and Tuenti, have experienced exponential growth in both profile registrations and social interactions. These networks allow people to share different information ranging from news, photos, videos, feelings, personal information or research activities. The rapid growth of OSNs has triggered a dramatic rise in malicious activities including spamming, fake accounts creation, phishing, and malware distribution. However, developing an efficient detection system that can identify malicious accounts, as well as their suspicious behaviors on the social networks, has been quite challenging. Researchers have proposed a number of features and methods to detect malicious accounts. This paper presents a comprehensive review of related studies that deal with detection of malicious accounts on social networking sites. The review focuses on four main categories, which include detection of spam accounts, fake accounts, compromised accounts, and phishing. To group the studies, the taxonomy of the different features and methods used in the literature to identify malicious accounts and their behaviors are proposed. The review considered only social networking sites and excluded studies such as email spam detection. The significance of proposed features and methods, as well as their limitations, are analyzed. Key issues and challenges that require substantial research efforts are discussed. In conclusion, the paper identifies the important future research areas with the aim of advancing the development of scalable malicious accounts detection system in OSNs.