Timezone: »

Information Obfuscation of Graph Neural Networks
Peiyuan Liao · Han Zhao · Keyulu Xu · Tommi Jaakkola · Geoff Gordon · Stefanie Jegelka · Ruslan Salakhutdinov

Tue Jul 20 06:40 PM -- 06:45 PM (PDT) @ None

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes. In this paper, we study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance. Our method creates a strong defense against inference attacks, while only suffering small loss in task performance. Theoretically, we analyze the effectiveness of our framework against a worst-case adversary, and characterize an inherent trade-off between maximizing predictive accuracy and minimizing information leakage. Experiments across multiple datasets from recommender systems, knowledge graphs and quantum chemistry demonstrate that the proposed approach provides a robust defense across various graph structures and tasks, while producing competitive GNN encoders for downstream tasks.

Author Information

Peiyuan Liao (Carnegie Mellon University)
Han Zhao (University of Illinois at Urbana-Champaign)
Keyulu Xu (MIT)
Tommi Jaakkola (MIT)
Geoff Gordon (Carnegie Mellon University)
Stefanie Jegelka (Massachusetts Institute of Technology)
Russ Salakhutdinov (Carnegie Mellen University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors