Litcius/Paper detail

Label-Only Membership Inference Attack against Node-Level Graph Neural Networks

Mauro Conti, Jiaxin Li, Stjepan Picek, Jing Xu

202231 citationsDOIOpen Access PDF

Abstract

Graph Neural Networks (GNNs), inspired by Convolutional Neural Networks (CNNs), aggregate the message of nodes' neighbors and structure information to acquire expressive representations of nodes for node classification, graph classification, and link prediction. Previous studies have indicated that node-level GNNs are vulnerable to Membership Inference Attacks (MIAs), which infer whether a node is in the training data of GNNs and leak the node's private information, like the patient's disease history. The implementation of previous MIAs takes advantage of the models' probability output, which is infeasible if GNNs only provide the prediction label (label-only) for the input.

Topics & Concepts

Computer scienceInferenceGraphNode (physics)Convolutional neural networkArtificial neural networkAggregate (composite)Artificial intelligenceTheoretical computer scienceData miningMachine learningMaterials scienceEngineeringStructural engineeringComposite materialPrivacy-Preserving Technologies in DataAdvanced Graph Neural NetworksAdversarial Robustness in Machine Learning
Label-Only Membership Inference Attack against Node-Level Graph Neural Networks | Litcius