EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compression
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) have been widely used for graph analysis. Federated Graph Learning (FGL) is an emerging learning framework to collaboratively train graph data from various clients. Although FGL allows client data to remain localized, a malicious server can still steal client private data information through uploaded gradient. In this paper, we for the first time propose label distribution attacks (LDAs) on FGL that aim to infer the label distributions of the client-side data. Firstly, we observe that the effectiveness of LDA is closely related to the variance of node embeddings in GNNs. Next, we analyze the relation between them and propose a new attack named EC-LDA, which significantly improves the attack effectiveness by compressing node embeddings. Then, extensive experiments on node classification and link prediction tasks across six widely used graph datasets show that EC-LDA outperforms the SOTA LDAs. Specifically, EC-LDA can achieve the Cos-sim as high as 1.0 under almost all cases. Finally, we explore the robustness of EC-LDA under differential privacy protection and discuss the potential effective defense methods to EC-LDA. Our code is available at https://github.com/cheng-t/EC-LDA.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 21 May 2025.
Builds on
31 of 45 references.
References · 31
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2016Deep Learning with Differential Privacycited by 2,728
- 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
- 2019Deep Leakage from Gradientscited by 1,021
- 2019Graph Neural Networks for Social Recommendationcited by 714
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
- 2019Multi-scale Attributed Node Embeddingcited by 548
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
- 2020iDLG: Improved Deep Leakage from Gradientscited by 382
19 more
- 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 335
- 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
- 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 260
- 2022Reconstructing Training Data with Informed Adversariescited by 148
- 2014Label Distribution Learningcited by 124
- 2021Deep Learning with Label Differential Privacycited by 117
- 2020Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Modelscited by 116
- 2021Practical Blind Membership Inference Attack via Differential Comparisonscited by 78
- 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 67
- 2021Node-Level Differentially Private Graph Neural Networkscited by 43
- 2021Towards General Deep Leakage in Federated Learningcited by 40
- 2021Federated Graph Learning -- A Position Papercited by 35
- 2019Eavesdrop the Composition Proportion of Training Labels in Federated Learningcited by 27
- 2021Revealing and Protecting Labels in Distributed Trainingcited by 17
- 2024Distributionally Robust Graph-based Recommendation Systemcited by 17
- 2024A Topology-aware Graph Coarsening Framework for Continual Graph Learningcited by 11
- 2023DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Releasecited by 10
- 2022PPA: Preference Profiling Attack Against Federated Learningcited by 9
- 2021Label Inference Attacks from Log-loss Scorescited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.