Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks

Khang Tran, Phung Lai, Nhat Hai Phan, Issa Khalil, Yao Ma, Abdallah Khreishah, My T. Thai, Xintao Wu

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

1 Scopus citations

Abstract

Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAS) given their ability to learn joint representation from features and edges among nodes in graph data. To prevent privacy leakages in GNNs, we propose a novel heterogeneous randomized response (HeteroRR) mechanism to protect nodes' features and edges against PIAS under differential privacy (DP) guarantees, without an undue cost of data and model utility in training GNNs. Our idea is to balance the importance and sensitivity of nodes' features and edges in redistributing the privacy budgets since some features and edges are more sensitive or important to the model utility than others. As a result, we derive significantly better randomization probabilities and tighter error bounds at both levels of nodes' features and edges departing from existing approaches, thus enabling us to maintain high data utility for training GNNs. An extensive theoretical and empirical analysis using benchmark datasets shows that HeteroRR significantly outperforms various baselines in terms of model utility under rigorous privacy protection for both nodes' features and edges. That enables us to defend PIAs in DP-preserving GNNs effectively.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 IEEE International Conference on Big Data, Big Data 2022
EditorsShusaku Tsumoto, Yukio Ohsawa, Lei Chen, Dirk Van den Poel, Xiaohua Hu, Yoichi Motomura, Takuya Takagi, Lingfei Wu, Ying Xie, Akihiro Abe, Vijay Raghavan
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1582-1587
Number of pages6
ISBN (Electronic)9781665480451
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Big Data, Big Data 2022 - Osaka, Japan
Duration: Dec 17 2022Dec 20 2022

Publication series

NameProceedings - 2022 IEEE International Conference on Big Data, Big Data 2022

Conference

Conference2022 IEEE International Conference on Big Data, Big Data 2022
Country/TerritoryJapan
CityOsaka
Period12/17/2212/20/22

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Control and Optimization

Keywords

  • GNNs
  • differential privacy
  • privacy inference

Fingerprint

Dive into the research topics of 'Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks'. Together they form a unique fingerprint.

Cite this