Gradient Inversion Attack on Graph Neural Networks

2024-11-29 · Divya Anand Sinha, Yezi Liu, Ruijie Du, Yanning Shen

Graph federated learning is of essential importance for training over large graph datasets while protecting data privacy, where each client stores a subset of local graph data, while the server collects the local gradients and broadcasts only the aggregated gradients. Recent studies reveal that a malicious attacker can steal private image data from gradient exchanging of neural networks during federated learning. However, none of the existing works have studied the vulnerability of graph data and graph neural networks under such attack. To answer this question, the present paper studies the problem of whether private data can be recovered from leaked gradients in both node classification and graph classification tasks and { proposes a novel attack named Graph Leakage from Gradients (GLG)}. Two widely-used GNN frameworks are analyzed, namely GCN and GraphSAGE. The effects of different model settings on recovery are extensively discussed. Through theoretical analysis and empirical validation, it is shown that parts of the graph data can be leaked from the gradients.

📄 PDF Abstract BibTeX arXiv:2411.19440

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning Graph Classification Node Classification

Methods 이 논문이 사용한 방법론

GraphSAGE GraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen…

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Model Inversion Attacks against Graph Neural Networks

2022-09-16 · Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang 외

Many data mining tasks rely on graphs to model relational structures among individuals (nodes). Since relational data are often sensitive, there is an urgent need to evaluate the privacy risks in graph data. One famous p…

model Reinforcement Learning (RL)

FedGIG: Graph Inversion from Gradient in Federated Learning

2024-12-24 · Tianzhe Xiao, Yichen Li, Yining Qi, Haozhao Wang 외

Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, c…

Federated Learning Graph Learning

Model Inversion Attacks on Homogeneous and Heterogeneous Graph Neural Networks

2023-10-15 · Renyang Liu, Wei Zhou, Jinhong Zhang, Xiaoyuan Liu 외

Recently, Graph Neural Networks (GNNs), including Homogeneous Graph Neural Networks (HomoGNNs) and Heterogeneous Graph Neural Networks (HeteGNNs), have made remarkable progress in many physical scenarios, especially in c…

GI-SMN: Gradient Inversion Attack against Federated Learning without Prior Knowledge

2024-05-06 · Jin Qian, Kaimin Wei, Yongdong Wu, Jilian Zhang 외

Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion…

Federated Learning Privacy Preserving

GRAIN: Exact Graph Reconstruction from Gradients

2025-03-03 · Maria Drencheva, Ivo Petrov, Maximilian Baader, Dimitar I. Dimitrov 외

Federated learning claims to enable collaborative model training among multiple clients with data privacy by transmitting gradient updates instead of the actual client data. However, recent studies have shown the client …

Federated Learning Graph Attention Graph Reconstruction