mlsanityData to 14 Oct 2026

Membership Inference Attacks and Privacy in Topic Modeling

arXiv 2403.04451 ↗First posted 7 Mar 2024cs.CR cs.CL cs.LGcited by 1

On the map: LLM safety and security → Membership inference attacks

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.

Key facts. Cited by 1 paper 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.

Builds on

13 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Membership Inference Attacks From First Principles7 Dec

Other references · 12

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  2. 2020Extracting Training Data from Large Language Modelscited by 2,189
  3. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  4. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  5. 2020Information Leakage in Embedding Modelscited by 203
  6. 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
  7. 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
  8. 2019Differentially Private SQL with Bounded User Contributioncited by 27
  9. 2020Differentially Private Set Unioncited by 14
  10. 2018An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithmcited by 4
  11. 2020Latent Dirichlet Allocation Model Training with Differential Privacycited by 4
  12. 2016Private Topic Modelingcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integritycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks
  2. 2025The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
  3. 2024On the Privacy Risk of In-context Learning
  4. 2024Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions
  5. 2024SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks
  6. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Models
  7. 2025A Survey on Privacy Risks and Protection in Large Language Models
  8. 2025Membership Inference Attacks on Large-Scale Models: A Survey