# EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compression

arXiv: https://arxiv.org/abs/2505.15140 · HTML: https://mlsanity.com/paper/2505.15140/

## Key facts

- Cited by 1 papers 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 (most cited first, 30 of 31)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [Reconstructing Training Data with Informed Adversaries](https://mlsanity.com/paper/2201.04845/) (2022)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [Practical Blind Membership Inference Attack via Differential Comparisons](https://mlsanity.com/paper/2101.01341/) (2021)
- [Eluding Secure Aggregation in Federated Learning via Model Inconsistency](https://mlsanity.com/paper/2111.07380/) (2021)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [Towards General Deep Leakage in Federated Learning](https://mlsanity.com/paper/2110.09074/) (2021)
- [Federated Graph Learning -- A Position Paper](https://mlsanity.com/paper/2105.11099/) (2021)
- [Eavesdrop the Composition Proportion of Training Labels in Federated Learning](https://mlsanity.com/paper/1910.06044/) (2019)
- [Revealing and Protecting Labels in Distributed Training](https://mlsanity.com/paper/2111.00556/) (2021)
- [Distributionally Robust Graph-based Recommendation System](https://mlsanity.com/paper/2402.12994/) (2024)
- [A Topology-aware Graph Coarsening Framework for Continual Graph Learning](https://mlsanity.com/paper/2401.03077/) (2024)
- [DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release](https://mlsanity.com/paper/2311.14056/) (2023)
- [PPA: Preference Profiling Attack Against Federated Learning](https://mlsanity.com/paper/2202.04856/) (2022)

## Built on by (most cited first, 1 of 1)

- [Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks](https://mlsanity.com/paper/2602.00407/) (2026)

## 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.