# Membership Inference Attacks and Privacy in Topic Modeling

arXiv: https://arxiv.org/abs/2403.04451 · HTML: https://mlsanity.com/paper/2403.04451/

## 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 13 of its 39 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [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)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Topic-Guided Variational Autoencoders for Text Generation](https://mlsanity.com/paper/1903.07137/) (2019)
- [Differentially Private SQL with Bounded User Contribution](https://mlsanity.com/paper/1909.01917/) (2019)
- [Differentially Private Set Union](https://mlsanity.com/paper/2002.09745/) (2020)
- [An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm](https://mlsanity.com/paper/1805.10341/) (2018)
- [Latent Dirichlet Allocation Model Training with Differential Privacy](https://mlsanity.com/paper/2010.04391/) (2020)
- [Private Topic Modeling](https://mlsanity.com/paper/1609.04120/) (2016)

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

- [Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity](https://mlsanity.com/paper/2503.09365/) (2025)

## Abstract (arXiv)

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this work, we propose an attack against topic models that can confidently identify members of the training data in Latent Dirichlet Allocation. Our results suggest that the privacy risks associated with generative modeling are not restricted to large neural models. Additionally, to mitigate these vulnerabilities, we explore differentially private (DP) topic modeling. We propose a framework for private topic modeling that incorporates DP vocabulary selection as a pre-processing step, and show that it improves privacy while having limited effects on practical utility.