Abstract
Successful profile cloning attacks have far-reaching consequences for the victims. People whose profiles are cloned suffer defamation, mistrust, loss of job, interdiction, public disgrace, dent of reputation, and defrauding. This chapter aims to identify and propose a model that detects profile cloning attacks on online social network platforms. The proposed model is based on unsupervised machine learning clustering and statistical similarity verification methods for the filtration of profiles. The model computes statistical values for attribute similarity measure (ASM) and friends network similarity measure (FNSM). The model has a precision score of 100%. The attribute weight and friends network similarity measures show percentile figures ranging from 0.45 to 1.00. Profile accounts that fall within this range for both ASM and FNSM measures are likely to turn out to be cloned. The higher the figures, the more the suspicion of being a fake account to the supposed original one. The strength of the model is that it exposes the actual clone using the outcome of the computation.
TopIntroduction
Advancements in technology and web development have given rise to social networking among people using the internet. The Internet provides web services such as e-mails, e-commerce website services, and online social network site services. The increasing use of the internet has been remarkable. A recent report shows that the global human resource of almost 2.6 million, representing 7.9 percent permanently work from home using the internet, even before the COVID-19 pandemic. After the outbreak of the pandemic, about 18 percent of workers work from home (Venkatesha et al., 2021). One of the fast-growing internet services is the online social network (OSN) sites. Online social network platforms enable people to register and share messages, share career interests, ideas, audio, and images. It allows enhancing social skills, building, and networking among businesses and partners (Jain et al., 2021b; Rao et al., 2020b; Roy & Chahar, 2021).
Several people connect on OSNs including presidents, business leaders, and prominent personalities to share information. The information shared on these platforms may include names, careers and professions, birth dates, photos, and videos. People also read what others have to share. A large number of users patronize OSN services. Currently, even governmental and non-governmental agencies, businesses, and organizations have operational accounts on at least one of these OSN sites to reach out and receive information from the populace (Jain et al., 2021b; Kharaji et al., 2014). Recent statistics show that in the first quarter of 2020, Facebook had more than 2.5 million monthly active users and Twitter chalks up to 330 million active users in a day (Hu et al., 2021; Jain et al., 2021b; Kumar, Kumar Gupta, et al., 2013). The OSN users share large amounts of data with friends in their network by the very nature of OSNs.
Although OSN services provide several benefits, there also exist inherent vulnerabilities. Users especially those who are new to these platforms, oftentimes, are less selective and security conscious, thereby inviting and accepting friends of varied backgrounds. People turn to accept all manner of friends including wrongdoers – malicious intruders, who prey on innocent users by misconducting themselves in cyber-bullying, spamming, phishing, and above all, engaging in profile cloning (Liyanage & Premarathne, 2021a; Rao et al., 2020b). While the core principles that underpin social networking are openness, connecting, and sharing with others, these give rise to unscrupulous OSN users preying on the profile accounts of unsuspecting persons, invading their privacy, and cloning their profiles. There has been exposure to extremely volatile information by OSN platform users (Rao et al., 2020a). What is more alarming is the lack of privacy and its related crime (Liyanage & Premarathne, 2019; Venkatesha et al., 2021). Personal and corporate information which must be protected from public consumption are rather exposed, out of naivety and ignorance of privacy security settings. At large, online social sites are susceptible to risks such as phishing attacks, malware attacks, cyberbullying, and identity theft (Mustafa et al., 2019).
Key Terms in this Chapter
Suspicious Profiles: A suspicious profile is a profile having common or similar attributes with the real or original profile such that there is highly no distinction between the two. Profile attributes such as first name, last name, and user name, are taken from a profile that the owner is willing to duplicate profile of his/hers. The data gathered is used to create test queries in search engines available on OSNs. The outcome of the search is used to create a suspected list of profiles-accounts which is further screened.
Cross-Site Profiles: Cross-site profiles are user accounts on two or more social networking sites that bear a resemblance in nature (appearance and content). Often social networking enthusiasts have multiple accounts across various sites available to them and keep them active or otherwise. In contrast, a user account or profile on one social site is secretly replicated by an intruder on another social site and lures friends of the original account user’s friends on the new social site to accept his friend request the blind side of the original account user's. When an account is stolen from one site and replicated by another person on a different site it is known as cross-site profile cloning.
Profile Evaluation: It is a method of gathering suspected profiles for investigation based on attribute similarity and relationship strength measurements in comparison to the original profile. A clone profile is identified when the quantity of profile similarity exceeds a predetermined threshold of relationship and is less than others.
Active Friend: An active friend in social networking is said to be two or more users who frequently share posts, otherwise, communicate very often. It represents the interaction frequency of a user with his/her friend(s) in the network.
Same-Site Profiles: Same-site profiles are profiles that exist on one particular social networking site. When two or more profiles on the same site appear similar or share likeness, it is believed that one is a clone of the other.
Profile Cloning (Fake Profile): According to Bródka & Sobas (2014) AU114: The in-text citation "Bródka & Sobas (2014)" is not in the reference list. Please correct the citation, add the reference to the list, or delete the citation. , a fake profile is an attempt to duplicate or reproduce illegally the credentials or biodata of an existing account by creating an identical one without the original account holder's knowledge or permission to eavesdrop or tap exchanges between the original profile owner and friends.
Social Network: An online platform networking is a collection of social structures among a group of people that are linked in some way. People may share their interests, activities, and circle of contacts with their families, loves, and friends thanks to social networks' offer of social presence via the web and virtual environment. An OSN platform networking is a collection or a community of people that are linked in some way. People may share their interests, activities, and circle of contacts with their families, loves, and friends thanks to social networks' offer of social presence via the web and virtual environment.
Internet: The Internet is a facility used to provide web services such as e-mails, e-commerce website services, and online social network site services.
Attribute Similarity: Attribute similarity is the comparison between the same fields of two or more profiles to measure the degree of likeness or similarity in contents. The attribute similarity metric determines how comparable a couple of profile accounts are concerning the weight of similar attributes in their fields. Users' profiles frequently contain categorical data in each field, according to the Similarity Measure. The fundamental measures to compare two attributes are if two profiles have the same value in the same field. Return 1 if the condition is true; else, return 0.
OSN website: Online Social Networking (OSN) sites provide a common pattern for the required profile information and the fields allow entries of all kinds including hobbies, relationships, and career interests. There are also options for introducing additional fields.