Guardado en:
Detalles Bibliográficos
Autores principales: Li, Kunhao, Wu, Di, Bai, Jun, Xu, Jing, Yang, Lei, Zhang, Ziyi, Song, Yiliao, Yang, Wencheng, Cai, Taotao, Li, Yan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.19964
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916865096286208
author Li, Kunhao
Wu, Di
Bai, Jun
Xu, Jing
Yang, Lei
Zhang, Ziyi
Song, Yiliao
Yang, Wencheng
Cai, Taotao
Li, Yan
author_facet Li, Kunhao
Wu, Di
Bai, Jun
Xu, Jing
Yang, Lei
Zhang, Ziyi
Song, Yiliao
Yang, Wencheng
Cai, Taotao
Li, Yan
contents Graph-structured data is prevalent in many real-world applications, including social networks, financial systems, and molecular biology. Graph Neural Networks (GNNs) have become the de facto standard for learning from such data due to their strong representation capabilities. As GNNs are increasingly deployed in federated learning (FL) settings to preserve data locality and privacy, new privacy threats arise from the interaction between graph structures and decentralized training. In this paper, we present the first systematic study of cross-client membership inference attacks (CC-MIA) against node classification tasks of federated GNNs (FedGNNs), where a malicious client aims to infer which client owns the given data. Unlike prior centralized-focused work that focuses on whether a sample was included in training, our attack targets sample-to-client attribution, a finer-grained privacy risk unique to federated settings. We design a general attack framework that exploits FedGNNs' aggregation behaviors, gradient updates, and embedding proximity to link samples to their source clients across training rounds. We evaluate our attack across multiple graph datasets under realistic FL setups. Results show that our method achieves high performance on both membership inference and ownership identification. Our findings highlight a new privacy threat in federated graph learning-client identity leakage through structural and model-level cues, motivating the need for attribution-robust GNN design.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19964
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
Li, Kunhao
Wu, Di
Bai, Jun
Xu, Jing
Yang, Lei
Zhang, Ziyi
Song, Yiliao
Yang, Wencheng
Cai, Taotao
Li, Yan
Machine Learning
Graph-structured data is prevalent in many real-world applications, including social networks, financial systems, and molecular biology. Graph Neural Networks (GNNs) have become the de facto standard for learning from such data due to their strong representation capabilities. As GNNs are increasingly deployed in federated learning (FL) settings to preserve data locality and privacy, new privacy threats arise from the interaction between graph structures and decentralized training. In this paper, we present the first systematic study of cross-client membership inference attacks (CC-MIA) against node classification tasks of federated GNNs (FedGNNs), where a malicious client aims to infer which client owns the given data. Unlike prior centralized-focused work that focuses on whether a sample was included in training, our attack targets sample-to-client attribution, a finer-grained privacy risk unique to federated settings. We design a general attack framework that exploits FedGNNs' aggregation behaviors, gradient updates, and embedding proximity to link samples to their source clients across training rounds. We evaluate our attack across multiple graph datasets under realistic FL setups. Results show that our method achieves high performance on both membership inference and ownership identification. Our findings highlight a new privacy threat in federated graph learning-client identity leakage through structural and model-level cues, motivating the need for attribution-robust GNN design.
title Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2507.19964