# The Model's Language Matters: A Comparative Privacy Analysis of LLMs

arXiv: https://arxiv.org/abs/2510.08813 · HTML: https://mlsanity.com/paper/2510.08813/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [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)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Enhanced Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/2111.09679/) (2021)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [Counterfactual Memorization in Neural Language Models](https://mlsanity.com/paper/2112.12938/) (2021)
- [Rethinking LLM Memorization through the Lens of Adversarial Compression](https://mlsanity.com/paper/2404.15146/) (2024)
- [Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?](https://mlsanity.com/paper/2104.07762/) (2021)
- [Membership Inference Attack Susceptibility of Clinical Language Models](https://mlsanity.com/paper/2104.08305/) (2021)
- [Learnable Privacy Neurons Localization in Language Models](https://mlsanity.com/paper/2405.10989/) (2024)
- [SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation](https://mlsanity.com/paper/2506.12699/) (2025)
- [Quantifying the redundancy between prosody and text](https://mlsanity.com/paper/2311.17233/) (2023)
- [Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages](https://mlsanity.com/paper/2411.12240/) (2024)
- [What do complexity measures measure? Correlating and validating corpus-based measures of morphological complexity](https://mlsanity.com/paper/2204.05056/) (2022)

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

- [Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII](https://mlsanity.com/paper/2610.06093/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed across multilingual applications that handle sensitive data, yet their scale and linguistic variability introduce major privacy risks. Mostly evaluated for English, this paper investigates how language structure affects privacy leakage in LLMs trained on English, Spanish, French, and Italian medical corpora. We quantify six linguistic indicators and evaluate three attack vectors: extraction, counterfactual memorization, and membership inference. Results show that privacy vulnerability scales with linguistic redundancy and tokenization granularity: Italian exhibits the strongest leakage, while English shows higher membership separability. In contrast, French and Spanish display greater resilience due to higher morphological complexity. Overall, our findings provide the first quantitative evidence that language matters in privacy leakage, underscoring the need for language-aware privacy-preserving mechanisms in LLM deployments.