Adversary for Social Good: Leveraging Attribute-Obfuscating Attack to Protect User Privacy on Social Networks

Xiaoting Li, Lingwei Chen, Dinghao Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

As social networks become indispensable for people’s daily lives, inference attacks pose significant threat to users’ privacy where attackers can infiltrate users’ information and infer their private attributes. In particular, social networks are represented as graph-structured data, maintaining rich user activities and complex relationships among them. This enables attackers to deploy state-of-the-art graph neural networks (GNNs) to automate attribute inference attacks for users’ privacy disclosure. To address this challenge, in this paper, we leverage the vulnerability of GNNs to adversarial attacks, and propose a new graph adversarial method, called Attribute-Obfuscating Attack (AttrOBF) to mislead GNNs into misclassification and thus protect user attribute privacy against GNN-based inference attacks on social networks. Different from the prior attacks using perturbations on graph structure or node features, AttrOBF provides a more practical formulation by obfuscating optimal training user attribute values, and also advances the attribute obfuscation by solving the unavailability issue of test attribute annotations, black-box setting, bi-level optimization, and non-differentiable obfuscating operation. We demonstrate the effectiveness of AttrOBF on user attribute obfuscation by extensive experiments over three real-world social network datasets. We believe our work yields great potential of applying adversarial attacks to attribute protection on social networks.

Original languageEnglish (US)
Title of host publicationSecurity and Privacy in Communication Networks - 18th EAI International Conference, SecureComm 2022, Proceedings
EditorsFengjun Li, Kaitai Liang, Zhiqiang Lin, Sokratis K. Katsikas
PublisherSpringer Science and Business Media Deutschland GmbH
Pages710-728
Number of pages19
ISBN (Print)9783031255373
DOIs
StatePublished - 2023
Event18th EAI International Conference on Security and Privacy in Communication Networks, SecureComm 2022 - Virtual, Online
Duration: Oct 17 2022Oct 19 2022

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume462 LNICST
ISSN (Print)1867-8211
ISSN (Electronic)1867-822X

Conference

Conference18th EAI International Conference on Security and Privacy in Communication Networks, SecureComm 2022
CityVirtual, Online
Period10/17/2210/19/22

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this