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

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

Conti, M. (TU Delft Cyber Security; University of Padua)
Li, Jiaxin (University of Padua)
Picek, S. (TU Delft Cyber Security)
Xu, J. (TU Delft Cyber Security)

2022

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.

In this paper, we propose a label-only MIA against GNNs for node classification with the help of GNNs' flexible prediction mechanism, e.g., obtaining the prediction label of one node even when neighbors' information is unavailable. Our attacking method achieves around 60\% accuracy, precision, and Area Under the Curve (AUC) for most datasets and GNN models, some of which are competitive or even better than state-of-the-art probability-based MIAs implemented under our environment and settings. Additionally, we analyze the influence of the sampling method, model selection approach, and overfitting level on the attack performance of our label-only MIA. All of those three factors have an impact on the attack performance. Then, we consider scenarios where assumptions about the adversary's additional dataset (shadow dataset) and extra information about the target model are relaxed. Even in those scenarios, our label-only MIA achieves a better attack performance in most cases. Finally, we explore the effectiveness of possible defenses, including Dropout, Regularization, Normalization, and Jumping knowledge. None of those four defenses prevent our attack completely.

Machine learning
Membership inference attack
Graph neural networks

http://resolver.tudelft.nl/uuid:47a3bca4-3f36-4a4c-b531-164b0a7607fc

https://doi.org/10.1145/3560830.3563734

Association for Computing Machinery (ACM)

978-1-4503-9880-0

AISec 2022 - Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2022

15th ACM Workshop on Artificial Intelligence and Security, 2022-11-11, Los Angeles, United States

AISec 2022 - Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2022

Institutional Repository

conference paper

© 2022 M. Conti, Jiaxin Li, S. Picek, J. Xu