Neighborhood Watch: Privacy Risks in Seeded Local Combination Synthetic Data
cs.CR
Submitted: 2026-08-27
Updated: 2026-08-27
Comments: 16 pages main body, 20 pages with Appendix, 6 figures (including appendix), 7 tables (including appendix)
License: http://creativecommons.org/licenses/by/4.0/
The gist: Synthetic data is seen as a promising solution for sharing data in sensitive contexts.
Terminology
Abstract
Synthetic data is seen as a promising solution for sharing data in sensitive contexts. However, recent work on privacy attacks have shown that there are still significant residual risks, especially for synthetic data generations methods that are not based on formal approaches such as differential privacy. In this paper, we investigate the privacy risks associated with local combination approaches for generating synthetic data in which synthetic profiles are built by combining real neighbouring profiles. More precisely, we focus on three methods from this family, namely SMOTE, Simulant and Avatar, which have been recently used as a way to share 'anonymised data' in the healthcare domain. In particular, we conduct an extensive privacy analysis through a diverse set of attacks: membership inference, linkage and reconstruction attacks. Our results demonstrate substantial privacy leakage for all three methods, raising serious doubts about whether their outputs should be regarded as anonymous in practice.
Sources
- SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
- A Unified Framework for Quantifying Privacy Risk in Synthetic Data
- LOGAN: Membership Inference Attacks Against Generative Models
- Winning the NIST Contest: A scalable and general approach to differentially private synthetic data
- Membership Inference Attacks against Synthetic Data through Overfitting Detection
- Ensembling Membership Inference Attacks Against Tabular Generative Models
- Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills