Search the World's Largest Database of Information Science & Technology Terms & Definitions
InfInfoScipedia LogoScipedia
A Free Service of IGI Global Publishing House
Below please find a list of definitions for the term that
you selected from multiple scholarly research resources.

What is Attribute Similarity

Chapter 17
Risk Detection and Cyber Security for the Success of Contemporary Computing
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.
Published in Chapter:
Profile Clone Detection on Online Social Network Platforms
Anthony Doe Eklah (University of Ghana, Ghana), Winfred Yaokumah (University of Ghana, Ghana), and Justice Kwame Appati (University of Ghana, Ghana)
Copyright: © 2023 |Pages: 27
DOI: 10.4018/978-1-6684-9317-5.ch017
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.
Full Text Chapter Download: US $37.50 Add to Cart
eContent Pro Discount Banner
InfoSci OnDemandECP Editorial ServicesAGOSR