Massive content about user's social, personal and professional life stored on Online Social Networks (OSNs) has attracted not only the attention of researchers and social analysts but also the cyber criminals. These cyber criminals penetrate illegally into an OSN by establishing fake profiles or by designing bots and exploit the vulnerabilities of an OSN to carry out illegal activities. With the growth of technology cyber crimes have been increasing manifold. Daily reports of the security and privacy threats in the OSNs demand not only the intelligent automated detection systems that can identify and alleviate fake profiles in real time but also the reinforcement of the security and privacy laws to curtail the cyber crime. In this paper, we have studied various categories of fake profiles like compromised profiles, cloned profiles and online bots (spam-bots, social-bots, like-bots and influential-bots) on different OSN sites along with existing cyber laws to mitigate their threats. In order to design fake profile detection systems, we have highlighted different category of fake profile features which are capable to distinguish different kinds of fake entities from real ones. Another major challenges faced by researchers while building the fake profile detection systems is the unavailability of data specific to fake users. The paper addresses this challenge by providing extremely obliging data collection techniques along with some existing data sources. Furthermore, an attempt is made to present several machine learning techniques employed to design different fake profile detection systems.
Online Social Network Analysis (OSNA) is considered as one of the most emerging research fields. An Online Social Network (OSN) is the grouping of nodes (individuals, actors, organizations, nations, states or web pages etc.) around the world connected by a set of links (relationships, interactions, distances, hyperlinks, etc). Basically, OSNs refer to the web applications which are primarily designed to facilitate interaction, collaboration and share content among users. OSNs have changed the way people think, express, and socialize with outside world. Nowadays there are a huge number of social networking sites like Facebook, Twitter, Flicker, LinkedIn, Researchgate, etc. which are used by people to carry out their social and professional activities. Since the structure of OSNs bears a resemblance to the real-life communities and they hold a massive amount of user content, therefore, they are highly important to the researchers and several other disciplines including marketing, sociology, politics, etc. Marketing companies study OSNs to design viral marketing strategies and attain their potential customers, sociologists use them to analyze the human behavior and politicians use them to empower their political campaigns. [95,100,101]. Apart from researchers and business organizations, the universal popularity of OSNs has also attracted the attention of social criminals. These social criminals (or simply cyber criminals) exploit the exposure and weakness of an OSN to perform unlawful, misleading, malicious, or discriminatory operations. They penetrate into the social network either by creating fake profiles or by executing a number of identity theft attacks like cloning attacks, spoofing attacks [24], etc. on existing users to steal their credentials. These cybercriminals in every nation. The Information Technology Act in India has proved to be inadequate to a certain extent during its application. Adversaries are easily hacking into banking systems, social networking websites, e-commerce websites, etc. [107]. The tools and instruments needed to investigate cybercrime are quite different from those used to investigate ordinary crimes.
In order to control the cyber terrorism, more advanced automated methods for fake profile detection are needed. Also, the cyber laws need to be strengthened to handle cybercrimes across the boundaries. Cyber crime is a global phenomenon and therefore it should be tackled on the same level. Collectively it has been observed that the need of the hour is to identify a unique set of features to design effective model for detection of fake profiles on social networks and a worldwide uniform cyber laws in order to combat cyber crimes. In this paper, we aim to put everything about online malicious accounts at one place along with different cyber laws and commandments especially in Indian jurisdiction to curtail the fake profiles and their cybercrime.
OSNs are playing a vital role in contemporary life, people relying on them from different dimensions including social interactions, information sharing, and other daily activities. The negative impact on these OSNs by Fake profiles not only damages the user experience, but also the marketability and advertising potential of the given OSN. In respect to above circumstances, following are some key aspects which motivate this work to survey different kinds of suspicious identities on OSNS.
Online Fake profiles exist on every social networking platform with diverse aims. The different nature of fake profiles and the way they achieve their goals is still at its infancy. Furthermore, the cyber laws against cyber criminals are still generalised, inadequate with several shortcomings such as, there is ambiguity in terms, clear definitions for the important terms in law are not mentioned which can be dangerous and may have several degrees of interpretation.
As online fake users carry out their illicit operations based on their aim and architecture of the platform (online social networking websites), therefore, they may cuddle an exclusive set of attributes. Study of unique characteristics about every category of fake profiles can better aid in building efficient detection systems.
One of the major hurdles faced by researchers while building the fake profile detection systems is the unavailability of data specific to fake users on OSNs. Although very few, but there exist obliging data collection techniques which should be available to researchers in order to obtain the data to learn the fake profile detection models.
A number of studies towards detection of suspicious identities have been carried out so far using different machine learning based techniques on different platforms. The evolving research in this domain demands the appropriate techniques to deal with all kinds of bogus users. Therefore, all the techniques along with types of fake profiles should be available at a single place which assists to solve a particular problem with
This content is AI-processed based on open access ArXiv data.
