Construct New Graphs Using Information Bottleneck Against Property Inference Attacks

Chenhan Zhang1; Zhiyi Tian1; James J.Q. Yu2; Shui Yu1

10.1109/ICC45041.2023.10279148

2023-05-28

IEEE International Conference on Communications (IEEE ICC)

1938-1883

978-1-5386-7463-5

ICC 2023 - IEEE International Conference on Communications

2023-May

765-770

28 May-1 June 2023

Rome, Italy

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Graphs provide a unique representation of real-world data. However, recent studies found that inference attacks can extract private property information of graph data from trained graph neural networks (GNNs), which arouses privacy concerns about graph data, especially in collaborative learning systems where model information is more accessible. While there has been a few research efforts on the property inference attacks against GNNs, how to defend against such attacks has seldom been studied. In this paper, we propose to leverage the information bottleneck (IB) principle to defend against the property inference attacks. Particularly, we involve a threat model, where the attacker can extract graph property from the graph embedding developed by GNNs. To defend against the attacks, we use IB to construct new graph structures from the original graphs. The change in graph structures enables the new graphs to contain less information related to the property information of the original graphs, making it harder for attackers to infer property information of the original graphs from the graph embeddings. Meantime, the IB principle enables task-relevant information to be sufficiently contained in the new graph, enabling GNNs to develop accurate predictions. The experimental results demonstrate the efficacy of the proposed approach in resisting property inference attacks and developing accurate predictions.

Graph-structured data graph neural networks inference attacks information bottleneck

其他

英语

EI ; CPCI-S

Telecommunications

Telecommunications

WOS:001094862600123

20234815114442

Graph embeddings ; Graph structures ; Graphic methods

Database Systems:723.3 ; Artificial Intelligence:723.4

IEEE

1.School of Computer Science, University of Technology Sydney, Sydney, Australia
2.Dept. of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China

Chenhan Zhang,Zhiyi Tian,James J.Q. Yu,et al. Construct New Graphs Using Information Bottleneck Against Property Inference Attacks[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023:765-770.