mlsanityData to 14 Oct 2026

GRAIN: Exact Graph Reconstruction from Gradients

arXiv 2503.01838 ↗First posted 3 Mar 2025cs.LG cs.DCcited by 5

Not on the map. Why?

Abstract (arXiv)

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 privacy is still at risk due to the, so called, gradient inversion attacks which can precisely reconstruct clients' text and image data from the shared gradient updates. While these attacks demonstrate severe privacy risks for certain domains and architectures, the vulnerability of other commonly-used data types, such as graph-structured data, remain under-explored. To bridge this gap, we present GRAIN, the first exact gradient inversion attack on graph data in the honest-but-curious setting that recovers both the structure of the graph and the associated node features. Concretely, we focus on Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) -- two of the most widely used frameworks for learning on graphs. Our method first utilizes the low-rank structure of GNN gradients to efficiently reconstruct and filter the client subgraphs which are then joined to complete the input graph. We evaluate our approach on molecular, citation, and social network datasets using our novel metric. We show that GRAIN reconstructs up to 80% of all graphs exactly, significantly outperforming the baseline, which achieves up to 20% correctly positioned nodes.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

26 of 39 references.

References · 26

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  7. 2019Deep Leakage from Gradientscited by 1,021
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  9. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  10. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  11. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  12. 2021Federated Graph Classification over Non-IID Graphscited by 114
14 more
  1. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 108
  2. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 73
  3. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  4. 2021TAG: Gradient Attack on Transformer-based Language Modelscited by 63
  5. 2022LAMP: Extracting Text from Gradients with Language Model Priorscited by 54
  6. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 53
  7. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  8. 2021Towards General Deep Leakage in Federated Learningcited by 40
  9. 2021FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Predictioncited by 26
  10. 2021Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Settingcited by 19
  11. 2024SPEAR:Exact Gradient Inversion of Batches in Federated Learningcited by 15
  12. 2021STFL: A Temporal-Spatial Federated Learning Framework for Graph Neural Networkscited by 14
  13. 2024DAGER: Exact Gradient Inversion for Large Language Modelscited by 14
  14. 2022TabLeak: Tabular Data Leakage in Federated Learningcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learningcited by 3
  2. 2025Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysiscited by 0
  3. 2025GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearningcited by 0
  4. 2026Fed-Listing: Federated Label Distribution Inference in Graph Neural Networkscited by 0
  5. 2026TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimizationcited by 0