۱- Introduction

۲- Research related to OSN security threats

۳- Existing models

۴- Recent work on privacy-preserving fake profile detection

۵- Comparison of current techniques

۶- Open issues

۷- Conclusion

References

Abstract

In the present era, online social networks are the most popular and rapid information propagation applications on the Internet. People of all ages spend most of their time on social networking sites. Huge volumes of data are being created and shared through social networks around the world. These interests have given rise to illegitimate users who engage in fraudulent activities against social network users. On 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, most of which use the huge volume of unstructured data generated from social networks, have been proposed for the detection of fake profiles. This study presents a survey of the existing and latest technical work on fake profile detection.

Introduction

Social media is growing incredibly fast these days, which is important for marketing campaigns and celebrities who try to promote themselves by growing their base of followers and fans. However, fake profiles, created seemingly on behalf of organizations or people, can damage their reputations and decrease their numbers of likes and followers. They also suffer from fake updates and unnecessary confusion with other people. Fake profiles of all kinds create negative effects that counteract the advantages of social media for businesses in advertising and marketing and pave the way for cyber bullying. The users have different concerns regarding their privacy in an online environment. Fire et al. [1] described the threats of which users are unaware in Online Social Networks (OSNs). These include loss of privacy, identity theft, malware, fake profiles (Sybil’s/social bots), and sexual harassment, among others. OSNs have billions of registered users. Facebook is the most famous OSN with more than a billion active users. There are basically four kinds of threats in OSN: classic threats, modern threats, combination threats, and threats targeting children. Several suggested solutions to these threats fall into three categories: operator, commercial, and academic solutions. The mechanisms in each of these categories can help to overcome the security threats in OSNs. Social engineering [2] is the primary cause of many kinds of security and privacy threats in OSNs. The main approaches to social engineering are social-technical, technical, physical, and social, and these are generally carried out using software or humans. The channels for social engineering are e-mail, instant messenger, telephone, Voice over Internet Protocol (VoIP), OSN, cloud, websites and physical channels.