A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
Authors:
- Enyan DaiEDEnyan Dai
- Limeng CuiLCLimeng Cui
- Zhengyang WangZWZhengyang Wang
- Xianfeng TangXTXianfeng Tang
- Yinghan WangYWYinghan Wang
- Monica ChengMCMonica Cheng
- Bing YinBYBing Yin
- Suhang WangSWSuhang Wang
Preprint
Abstract
Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker. In addition, training data of GNNs can be leaked under membership inference attacks. This largely hinders the adoption of GNNs in high-stake domains such as e-commerce, finance and bioinformatics. Though investigations have been made in conducting robust predictions and protecting membership privacy, they generally fail to simultaneously consider the robustness and membership privacy. Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs. Our analysis shows that Information Bottleneck (IB) can help filter out noisy information and regularize the predictions on labeled samples, which can benefit robustness and membership privacy. However, structural noises and lack of labels in node classification challenge the deployment of IB on graph-structured data. To mitigate these issues, we propose a novel graph information bottleneck framework that can alleviate structural noises with neighbor bottleneck. Pseudo labels are also incorporated in the optimization to minimize the gap between the predictions on the labeled set and unlabeled set for membership privacy. Extensive experiments on real-world datasets demonstrate that our method can give robust predictions and simultaneously preserve membership privacy.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and ExplainabilityMachine Intelligence Research, 2024
- Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications2021
- A weighted patient network-based framework for predicting chronic diseases using graph neural networksScientific Reports, 2021
- Molecular generative Graph Neural Networks for Drug DiscoveryNeurocomputing, 2021
- A Semi-Supervised Graph Attentive Network for Financial Fraud Detection2019
- Robust Graph Convolutional Networks Against Adversarial Attacks2019
- Machine Learning with Membership Privacy using Adversarial Regularization2018
- Adversarial Attacks on Neural Networks for Graph Data2018
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
- Deep Learning with Differential Privacy2016