# How to Combine Membership-Inference Attacks on Multiple Updated Models

arXiv: https://arxiv.org/abs/2205.06369 · HTML: https://mlsanity.com/paper/2205.06369/

## Key facts

- Cited by 8 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 21 of its 37 references that are in the map.
- First posted on arXiv 12 May 2022.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://mlsanity.com/paper/2101.04535/) (2021)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [Machine Learning with Membership Privacy using Adversarial Regularization](https://mlsanity.com/paper/1807.05852/) (2018)
- [Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference](https://mlsanity.com/paper/1906.11798/) (2019)
- [Membership Leakage in Label-Only Exposures](https://mlsanity.com/paper/2007.15528/) (2020)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)
- [Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning](https://mlsanity.com/paper/1904.01067/) (2019)
- [Revisiting Membership Inference Under Realistic Assumptions](https://mlsanity.com/paper/2005.10881/) (2020)
- [Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds](https://mlsanity.com/paper/1405.7085/) (2014)
- [Analyzing Information Leakage of Updates to Natural Language Models](https://mlsanity.com/paper/1912.07942/) (2019)
- [Fingerprinting Codes and the Price of Approximate Differential Privacy](https://mlsanity.com/paper/1311.3158/) (2013)
- [Eavesdrop the Composition Proportion of Training Labels in Federated Learning](https://mlsanity.com/paper/1910.06044/) (2019)

## Built on by (most cited first, 8 of 8)

- [Measuring Forgetting of Memorized Training Examples](https://mlsanity.com/paper/2207.00099/) (2022)
- [Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries](https://mlsanity.com/paper/2210.10750/) (2022)
- [MoPe: Model Perturbation-based Privacy Attacks on Language Models](https://mlsanity.com/paper/2310.14369/) (2023)
- [Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models](https://mlsanity.com/paper/2402.17012/) (2024)
- [Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting](https://mlsanity.com/paper/2306.05093/) (2023)
- [Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach](https://mlsanity.com/paper/2604.21197/) (2026)
- [Information Leakage from Data Updates in Machine Learning Models](https://mlsanity.com/paper/2309.11022/) (2023)
- [Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2406.00249/) (2024)

## Abstract (arXiv)

A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training data. Most MI research focuses on the case of a single standalone model, while production machine-learning platforms often update models over time, on data that often shifts in distribution, giving the attacker more information. This paper proposes new attacks that take advantage of one or more model updates to improve MI. A key part of our approach is to leverage rich information from standalone MI attacks mounted separately against the original and updated models, and to combine this information in specific ways to improve attack effectiveness. We propose a set of combination functions and tuning methods for each, and present both analytical and quantitative justification for various options. Our results on four public datasets show that our attacks are effective at using update information to give the adversary a significant advantage over attacks on standalone models, but also compared to a prior MI attack that takes advantage of model updates in a related machine-unlearning setting. We perform the first measurements of the impact of distribution shift on MI attacks with model updates, and show that a more drastic distribution shift results in significantly higher MI risk than a gradual shift. Our code is available at https://www.github.com/stanleykywu/model-updates.