# Secure Deep Graph Generation with Link Differential Privacy

arXiv: https://arxiv.org/abs/2005.00455 · HTML: https://mlsanity.com/paper/2005.00455/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2020.

## Built on by (most cited first, 24 of 24)

- [Subgraph Federated Learning with Missing Neighbor Generation](https://mlsanity.com/paper/2106.13430/) (2021)
- [Source Inference Attacks in Federated Learning](https://mlsanity.com/paper/2109.05659/) (2021)
- [Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction](https://mlsanity.com/paper/2202.09025/) (2022)
- [A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systems](https://mlsanity.com/paper/2206.04149/) (2022)
- [Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation](https://mlsanity.com/paper/2202.07253/) (2022)
- [Deep Efficient Private Neighbor Generation for Subgraph Federated Learning](https://mlsanity.com/paper/2401.04336/) (2024)
- [Privacy-Preserving Graph Machine Learning from Data to Computation: A Survey](https://mlsanity.com/paper/2307.04338/) (2023)
- [A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy](https://mlsanity.com/paper/2206.03492/) (2022)
- [Poincar'e Differential Privacy for Hierarchy-Aware Graph Embedding](https://mlsanity.com/paper/2312.12183/) (2023)
- [Graph Generative Model for Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2207.04396/) (2022)
- [Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation](https://mlsanity.com/paper/2210.00538/) (2022)
- [Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation](https://mlsanity.com/paper/2309.03190/) (2023)
- [FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2104.07145/) (2021)
- [Cross-Network Social User Embedding with Hybrid Differential Privacy Guarantees](https://mlsanity.com/paper/2209.01539/) (2022)
- [Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views](https://mlsanity.com/paper/2308.10077/) (2023)
- [Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks](https://mlsanity.com/paper/2211.05766/) (2022)
- [Privacy-preserving Graph Analytics: Secure Generation and Federated Learning](https://mlsanity.com/paper/2207.00048/) (2022)
- [AdvSGM: Differentially Private Graph Learning via Adversarial Skip-gram Model](https://mlsanity.com/paper/2503.21426/) (2025)
- [Structure-Preference Enabled Graph Embedding Generation under Differential Privacy](https://mlsanity.com/paper/2501.03451/) (2025)
- [Adversarial Signed Graph Learning with Differential Privacy](https://mlsanity.com/paper/2512.00307/) (2025)
- [CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology](https://mlsanity.com/paper/2512.19736/) (2025)
- [FairGFL: Privacy-Preserving Fairness-Aware Federated Learning with Overlapping Subgraphs](https://mlsanity.com/paper/2512.23235/) (2025)
- [Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs](https://mlsanity.com/paper/2602.06700/) (2026)
- [Differentially Private Modeling of Disease Transmission within Human Contact Networks](https://mlsanity.com/paper/2604.07493/) (2026)

## Abstract (arXiv)

Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes). Since relational data are often sensitive, we aim to seek effective approaches to generate utility-preserved yet privacy-protected structured data. In this paper, we leverage the differential privacy (DP) framework to formulate and enforce rigorous privacy constraints on deep graph generation models, with a focus on edge-DP to guarantee individual link privacy. In particular, we enforce edge-DP by injecting proper noise to the gradients of a link reconstruction-based graph generation model, while ensuring data utility by improving structure learning with structure-oriented graph discrimination. Extensive experiments on two real-world network datasets show that our proposed DPGGAN model is able to generate graphs with effectively preserved global structure and rigorously protected individual link privacy.