GraphDLG: Exploring Deep Leakage from Gradients in Federated Graph Learning

• URL: http://arxiv.org/abs/2601.19745v1
• Date: Tue, 27 Jan 2026 16:06:48 GMT
• Title: GraphDLG: Exploring Deep Leakage from Gradients in Federated Graph Learning
• Authors: Shuyue Wei, Wantong Chen, Tongyu Wei, Chen Gong, Yongxin Tong, Lizhen Cui,
• Abstract summary: Federated graph learning (FGL) has emerged as a promising privacy-preserving paradigm that enables distributed graph learning across multiple data owners.<n>A critical privacy concern in FGL is whether an adversary can recover raw data from shared gradients, a vulnerability known as deep leakage from gradients (DLG)<n>We propose GraphDLG, a novel approach to recover raw training graphs from shared gradients in FGL, which can utilize randomly generated graphs or client-side training graphs as auxiliaries to enhance recovery.
• Score: 33.0777343271681
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated graph learning (FGL) has recently emerged as a promising privacy-preserving paradigm that enables distributed graph learning across multiple data owners. A critical privacy concern in federated learning is whether an adversary can recover raw data from shared gradients, a vulnerability known as deep leakage from gradients (DLG). However, most prior studies on the DLG problem focused on image or text data, and it remains an open question whether graphs can be effectively recovered, particularly when the graph structure and node features are uniquely entangled in GNNs. In this work, we first theoretically analyze the components in FGL and derive a crucial insight: once the graph structure is recovered, node features can be obtained through a closed-form recursive rule. Building on this analysis, we propose GraphDLG, a novel approach to recover raw training graphs from shared gradients in FGL, which can utilize randomly generated graphs or client-side training graphs as auxiliaries to enhance recovery. Extensive experiments demonstrate that GraphDLG outperforms existing solutions by successfully decoupling the graph structure and node features, achieving improvements of over 5.46% (by MSE) for node feature reconstruction and over 25.04% (by AUC) for graph structure reconstruction.

Related papers

• Dynamic Deep Graph Learning for Incomplete Multi-View Clustering with Masked Graph Reconstruction Loss [26.31060859315329]
  We propose a novel textbfDynamic Deep textbfGraph Learning for textbfIncomplete textbfMulti-textbfView textbfView textbfClustering with textbfMasked Graph Reconstruction Loss (DGIMVCM)<n>A graph convolutional embedding layer is then designed to extract primary features and refined dynamic view-specific graph structures, leveraging the global graph for imputation of missing views.
  arXiv  Detail & Related papers  (2025-11-14T11:26:38Z)
• FedGIG: Graph Inversion from Gradient in Federated Learning [15.10812005682518]
  This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG)<n>FedGIG is a novel GIA method specifically designed for graph-structured data.
  arXiv  Detail & Related papers  (2024-12-24T15:52:21Z)
• Gradient Inversion Attack on Graph Neural Networks [11.075042582118963]
  Malicious attackers can steal private image data from the exchange of neural networks during federated learning.<n>This paper studies the problem of whether private data can be reconstructed from leaked gradients in both node classification and graph classification tasks.<n>Two widely used GNN frameworks are analyzed, namely GCN and GraphSAGE.
  arXiv  Detail & Related papers  (2024-11-29T02:42:17Z)
• Community-Centric Graph Unlearning [10.906555492206959]
  We propose a novel Graph Structure Mapping Unlearning paradigm (GSMU) and a novel method based on it named Community-centric Graph Eraser (CGE)<n>CGE maps community subgraphs to nodes, thereby enabling the reconstruction of a node-level unlearning operation within a reduced mapped graph.
  arXiv  Detail & Related papers  (2024-08-19T05:37:35Z)
• GraphEdit: Large Language Models for Graph Structure Learning [14.16155596597421]
  Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data.<n>Existing GSL methods heavily depend on explicit graph structural information as supervision signals.<n>We propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data.
  arXiv  Detail & Related papers  (2024-02-23T08:29:42Z)
• GraphMAE: Self-Supervised Masked Graph Autoencoders [52.06140191214428]
  We present a masked graph autoencoder GraphMAE that mitigates issues for generative self-supervised graph learning. We conduct extensive experiments on 21 public datasets for three different graph learning tasks. The results manifest that GraphMAE--a simple graph autoencoder with our careful designs--can consistently generate outperformance over both contrastive and generative state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-05-22T11:57:08Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
  We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
  arXiv  Detail & Related papers  (2022-01-17T11:57:29Z)
• GraphMI: Extracting Private Graph Data from Graph Neural Networks [59.05178231559796]
  We present textbfGraph textbfModel textbfInversion attack (GraphMI), which aims to extract private graph data of the training graph by inverting GNN. Specifically, we propose a projected gradient module to tackle the discreteness of graph edges while preserving the sparsity and smoothness of graph features. We design a graph auto-encoder module to efficiently exploit graph topology, node attributes, and target model parameters for edge inference.
  arXiv  Detail & Related papers  (2021-06-05T07:07:52Z)
• Graph Contrastive Learning with Augmentations [109.23158429991298]
  We propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We show that our framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-10-22T20:13:43Z)
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings [53.58077686470096]
  We propose an end-to-end graph learning framework, namely Iterative Deep Graph Learning (IDGL) for jointly and iteratively learning graph structure and graph embedding. Our experiments show that our proposed IDGL models can consistently outperform or match the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-06-21T19:49:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.