# When Machine Learning Models Leak: An Exploration of Synthetic Training Data

arXiv: https://arxiv.org/abs/2310.08775 · HTML: https://mlsanity.com/paper/2310.08775/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 6 of 6)

- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [A Survey of Privacy Attacks in Machine Learning](https://mlsanity.com/paper/2007.07646/) (2020)
- [Synthetic Data -- Anonymisation Groundhog Day](https://mlsanity.com/paper/2011.07018/) (2020)
- [Variational Model Inversion Attacks](https://mlsanity.com/paper/2201.10787/) (2022)
- [Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models](https://mlsanity.com/paper/2201.09370/) (2022)

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

- [RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdata](https://mlsanity.com/paper/2602.09235/) (2026)

## Abstract (arXiv)

We investigate an attack on a machine learning model that predicts whether a person or household will relocate in the next two years, i.e., a propensity-to-move classifier. The attack assumes that the attacker can query the model to obtain predictions and that the marginal distribution of the data on which the model was trained is publicly available. The attack also assumes that the attacker has obtained the values of non-sensitive attributes for a certain number of target individuals. The objective of the attack is to infer the values of sensitive attributes for these target individuals. We explore how replacing the original data with synthetic data when training the model impacts how successfully the attacker can infer sensitive attributes.