An Enhanced Scammer Detection Model for Online Social Network Frauds Using Machine Learning - Research Overview

Aug 5, 2026

Upload by Anda

Online social networks increase exposure to fraud, as scammers create fake profiles and impersonate identities to lure users into dating scams, compromised accounts, and other social threats. This study presents an enhanced scammer detection model that uses user profile attributes and profile images as signals. It preprocesses profile data, extracts representative features, and applies machine learning classifiers to identify scammer profiles. Experiments on a dataset built for the study report 94.50% accuracy with low false positives, supporting early prevention of online fraud and improving safety.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

I. Introduction

Online social networks and their key features

Types of online social network fraud

Challenges in detecting replicated and fake profiles

Online dating growth and scammer-profile risk

An Enhanced Scammer Detection Model for Online Social Network Frauds Using Machine Learning Smita Bharne1, Pawan Bhaladhare2 1School of Computer Sciences and Engineering, Sandip University/ Ramrao Adik Institute of Technology, D. Y. Patil Deemed to be University Nashik, India [smita146@gmail.com](smita146@gmail.com) 2School of Computer Sciences and Engineering Sandip University Nashik, India [pawan_bh1@yahoo.com](pawan_bh1@yahoo.com) Abstract—The prevalence of online social networking increase in the risk of social network scams or fraud. Scammers often create fake profiles to trick unsuspecting users into fraudulent activities. Therefore, it is important to be able to identify these scammer profiles and prevent fraud such as dating scams, compromised accounts, and fake profiles. This study proposes an enhanced scammer detection model that utilizes user profile attributes and images to identify scammer profiles in online social networks. The approach involves preprocessing user profile data, extracting features, and machine learning algorithms for classification. The system was tested on a dataset created specifically for this study and was found to have an accuracy rate of 94.50% with low false-positive rates. The proposed approach aims to detect scammer profiles early on to prevent online social network fraud and ensure a safer environment for society and women’s safety. Keywords-Cyber security, Scammer profiles, Online social network frauds, Scammer detection model, Social threats, Compromised accounts, Fake profiles, Dating Fraud, Machine Learning. I. INTRODUCTION An online social network is medium that enables users to create personal profiles, connect with other users, and share information, content, and experiences with their network. Online social networks (OSN) can take various forms, including platforms (such as Facebook, Instagram, and Twitter,), dating platforms (such as Tumblr, Tinder, Bumble, Hinge, etc.), professional networking sites (such as LinkedIn), and online forums or discussion boards. They offer a range of features and tools that allow users to create and manage their online presence, build and maintain relationships with others, and access a wealth of information and resources [1] . Some of the key features of online social networks include: a) Personal profiles: users can create personal profiles that include information about themselves, such as their name, age, interests, and location. b) Connections: users can connect with other users on the platform, typically by sending friend or connection requests. c) Sharing: users can share various types of content, such as photos, videos, links, and status updates, with their network. d) Communication: Users can communicate with other users through messaging, commenting, and other forms of online communication. e) Privacy: most online social networks offer privacy settings that allow users to control who can see their content and interact with them on the platform. Overall, online social networks have transformed the way people connect and interact with each other, providing new opportunities for communication, collaboration, and socialization in the digital age. As the popularity of these OSN platforms increases, and fraudsters are taking advantage of the large number of users profiles to make OSN frauds. Online social network frauds happen for a variety of reasons, but most often they are motivated by financial gain or a desire to exploit other users for personal or professional gain. As fraudsters are creating the scam profile (false identity), it is typically for the purpose of deceiving or manipulating other users [2[[3] . Scam profiles may be used to perpetrate human-targeted frauds or other fraudulent activities, such as cyberbullying, dating fraud, compromised accounts, fake profiles, etc. It is important for users to be aware of these risks and to take steps to protect themselves and their personal information online. At

FAQs

Why is scammer-profile detection important in online social networks?

Because scammers create fake profiles and false identities to deceive users, enabling fraud such as dating scams, compromised accounts, and other social threats.

What does the proposed enhanced model use to identify scammer profiles?

It uses user profile attributes and profile images, combined through preprocessing, feature extraction, and machine learning-based classification.

What performance results are reported for the proposed approach?

The approach is tested on a study-specific dataset and achieves 94.50% accuracy with low false-positive rates.

Aug 5, 2026

Upload by Anda