Secure Deep Graph Generation with Link Differential Privacy

By Carl Yang, Ke Zhang, Liang Chen, Lichao Sun. 2020

52 citations recorded by the source corpus.

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 designated 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.

Subfields: Artificial Intelligence, Safety Research, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lichao Sun
2. Lingjuan Lyu
3. Carl Yang
4. Ke Zhang
5. Siu Ming Yiu
6. Xiaoxiao Li
7. Philip S. Yu
8. Bo Du

In Safety Research

1. Lichao Sun

In Sociology and Political Science

1. Lingjuan Lyu
2. Lichao Sun

Citations in the corpus

• Federated Model Distillation with Noise-Free Differential Privacy (2020, background): “…works mostly focus on the centralized differential privacy mechanism that requires a trusted party [Geyer et al. , 2017; McMahan et al. , 2018; Yang et al. , 2021], or local differential privacy, in which each user randomizes its gradients locally before sending it to an untrusted aggregator…”
• Subgraph Federated Learning with Missing Neighbor Generation (2021, background): “Graph mining emerges its significance in analyzing the informative graph data, which range from social networks to gene interaction networks (Yang et al., 2021; 2020b; 2019a).”