# PrivLava: Synthesizing Relational Data with Foreign Keys under Differential Privacy

arXiv: https://arxiv.org/abs/2304.04545 · HTML: https://mlsanity.com/paper/2304.04545/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2023.

## Built on by (most cited first, 11 of 11)

- [ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models](https://mlsanity.com/paper/2405.17724/) (2024)
- [Joint Relational Database Generation via Graph-Conditional Diffusion Models](https://mlsanity.com/paper/2505.16527/) (2025)
- [Synthetic Tabular Data: Methods, Attacks and Defenses](https://mlsanity.com/paper/2506.06108/) (2025)
- [Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilities](https://mlsanity.com/paper/2405.20959/) (2024)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [Chameleon: Foundation Models for Fairness-aware Multi-modal Data Augmentation to Enhance Coverage of Minorities](https://mlsanity.com/paper/2402.01071/) (2024)
- [RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models](https://mlsanity.com/paper/2506.00710/) (2025)
- [Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities](https://mlsanity.com/paper/2306.12609/) (2023)
- [Differentially Private Synthetic Data Generation for Relational Databases](https://mlsanity.com/paper/2405.18670/) (2024)
- [Towards Privacy-Preserving Relational Data Synthesis via Probabilistic Relational Models](https://mlsanity.com/paper/2409.04194/) (2024)
- [Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption](https://mlsanity.com/paper/2606.05129/) (2026)

## Abstract (arXiv)

Answering database queries while preserving privacy is an important problem that has attracted considerable research attention in recent years. A canonical approach to this problem is to use synthetic data. That is, we replace the input database R with a synthetic database R* that preserves the characteristics of R, and use R* to answer queries. Existing solutions for relational data synthesis, however, either fail to provide strong privacy protection, or assume that R contains a single relation. In addition, it is challenging to extend the existing single-relation solutions to the case of multiple relations, because they are unable to model the complex correlations induced by the foreign keys. Therefore, multi-relational data synthesis with strong privacy guarantees is an open problem. In this paper, we address the above open problem by proposing PrivLava, the first solution for synthesizing relational data with foreign keys under differential privacy, a rigorous privacy framework widely adopted in both academia and industry. The key idea of PrivLava is to model the data distribution in R using graphical models, with latent variables included to capture the inter-relational correlations caused by foreign keys. We show that PrivLava supports arbitrary foreign key references that form a directed acyclic graph, and is able to tackle the common case when R contains a mixture of public and private relations. Extensive experiments on census data sets and the TPC-H benchmark demonstrate that PrivLava significantly outperforms its competitors in terms of the accuracy of aggregate queries processed on the synthetic data.