A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy
Enyan Dai, Limeng Cui, Zhengyang Wang, Xianfeng Tang, Yinghan Wang,, Monica Cheng, Bing Yin, Suhang Wang

TL;DR
This paper introduces a unified graph information bottleneck framework that enhances the robustness of Graph Neural Networks against adversarial attacks and protects against membership inference attacks, addressing a critical privacy and security challenge.
Contribution
The work proposes a novel graph information bottleneck method that mitigates structural noise and incorporates pseudo labels to improve robustness and privacy in GNNs.
Findings
Achieves robust predictions on real-world datasets.
Simultaneously preserves membership privacy.
Effectively reduces structural noise in graph data.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Ethics and Social Impacts of AI · Privacy-Preserving Technologies in Data
Methodsfail
