In Loco Identity Fraud Detection Model using Statistical Analysis for Social Networking Sites: A Case Study with Facebook

Abstract

Rapid advancement in internet has made many Social Networking Sites (SNS) popular among a huge population, as various SNS accounts are interlinked with each other, spread of stored susceptible information of an individual is increasing. That has led to various security and privacy issues; one of them is impersonation or identity fraud. Identity fraud is the outcome of illegitimate or secret use of account owner’s identity to invade his/her account to track personal information. There are possibilities that known persons like parents, spouse, close friends, siblings who are interested in knowing what is going on in the account owner’s online life may check their personal SNS accounts. Hence an individual’s private SNS accounts can be invaded by an illegitimate user secretly without the knowledge of the account owner’s which results in compromise of private information. Thus, this paper proposes an in loco identity fraud detection strategy that employs a statistical analysis approach to constantly authenticate the authorized user, which outperforms the previously known technique. This strategy may be used to prevent stalkers from penetrating a person's SNS account in real time. The accuracy attained in this research is greater than 90% after 1 minute and greater than 95% after 5 minutes of observation.