Blind De-anonymization Attacks using Social Networks

TL;DR

This paper introduces a new structure-based de-anonymization attack on social network data that does not require prior seed knowledge, leveraging multi-hop neighborhood info and machine learning to improve accuracy and robustness.

Contribution

The paper presents a novel de-anonymization attack that overcomes previous limitations by eliminating the need for seed data and enhancing accuracy through multi-hop and machine learning techniques.

Findings

Outperforms existing methods by up to 10 times in accuracy.

Robust against data perturbations.

Effective without prior seed knowledge.

Abstract

It is important to study the risks of publishing privacy-sensitive data. Even if sensitive identities (e.g., name, social security number) were removed and advanced data perturbation techniques were applied, several de-anonymization attacks have been proposed to re-identify individuals. However, existing attacks have some limitations: 1) they are limited in de-anonymization accuracy; 2) they require prior seed knowledge and suffer from the imprecision of such seed information. We propose a novel structure-based de-anonymization attack, which does not require the attacker to have prior information (e.g., seeds). Our attack is based on two key insights: using multi-hop neighborhood information, and optimizing the process of de-anonymization by exploiting enhanced machine learning techniques. The experimental results demonstrate that our method is robust to data perturbations and significantly outperforms the state-of-the-art de-anonymization techniques by up to $10\times$ improvement.