# Evaluating Membership Inference Attacks in heterogeneous-data setups

arXiv: https://arxiv.org/abs/2502.18986 · HTML: https://mlsanity.com/paper/2502.18986/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 12 of 12)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Heterogeneity for the Win: One-Shot Federated Clustering](https://mlsanity.com/paper/2103.00697/) (2021)
- [ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models](https://mlsanity.com/paper/2102.02551/) (2021)
- [Differentially Private Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2111.09278/) (2021)
- [Mandoline: Model Evaluation under Distribution Shift](https://mlsanity.com/paper/2107.00643/) (2021)
- [LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation](https://mlsanity.com/paper/2303.12233/) (2023)
- [Investigating Membership Inference Attacks under Data Dependencies](https://mlsanity.com/paper/2010.12112/) (2020)
- [SoK: On Gradient Leakage in Federated Learning](https://mlsanity.com/paper/2404.05403/) (2024)
- [Bayes Security: A Not So Average Metric](https://mlsanity.com/paper/2011.03396/) (2020)

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

- [How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations](https://mlsanity.com/paper/2507.01487/) (2025)

## Abstract (arXiv)

Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was used for training. The attacker also has an auxiliary dataset to tune their inference algorithm. Attack papers commonly simulate setups in which the attacker's and the target's datasets are sampled from the same distribution. This setting is convenient to perform experiments, but it rarely holds in practice. ML literature commonly starts with similar simplifying assumptions (i.e., "i.i.d." datasets), and later generalizes the results to support heterogeneous data distributions. Similarly, our work makes a first step in the generalization of the MIA evaluation to heterogeneous data. First, we design a metric to measure the heterogeneity between any pair of tabular data distributions. This metric provides a continuous scale to analyze the phenomenon. Second, we compare two methodologies to simulate a data heterogeneity between the target and the attacker. These setups provide opposite performances: 90% attack accuracy vs. 50% (i.e., random guessing). Our results show that the MIA accuracy depends on the experimental setup; and even if research on MIA considers heterogeneous data setups, we have no standardized baseline of how to simulate it. The lack of such a baseline for MIA experiments poses a significant challenge to risk assessments in real-world machine learning scenarios.