Generation of Automatic and Realistic Artificial Profiles

TL;DR

This paper introduces 'ProfileGen', an automated method for creating highly realistic artificial profiles for professional social networks, aiding in the detection of malicious activities by cybercriminals.

Contribution

The paper presents a novel automated approach to generate realistic artificial profiles, focusing on education and employment data for honeypots in OSNs.

Findings

Profiles generated are indistinguishable from real data according to expert evaluation.

The method effectively extrapolates characteristics of real profiles to produce convincing artificial profiles.

Applicable to various social network security applications.

Abstract

Online social networks (OSNs) are abused by cyber criminals for various malicious activities. One of the most effective approaches for detecting malicious activity in OSNs involves the use of social network honeypots - artificial profiles that are deliberately planted within OSNs in order to attract abusers. Honeypot profiles have been used in detecting spammers, potential cyber attackers, and advanced attackers. Therefore, there is a growing need for the ability to reliably generate realistic artificial honeypot profiles in OSNs. In this research we present 'ProfileGen' - a method for the automated generation of profiles for professional social networks, giving particular attention to producing realistic education and employment records. 'ProfileGen' creates honeypot profiles that are similar to actual data by extrapolating the characteristics and properties of real data items. Evaluation by 70 domain experts confirms the method's ability to generate realistic artificial profiles that are indistinguishable from real profiles, demonstrating that our method can be applied to generate realistic artificial profiles for a wide range of applications.