# Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

arXiv: https://arxiv.org/abs/2606.06946 · HTML: https://mlsanity.com/paper/2606.06946/

## Key facts

- Cited by 4 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 31 of its 48 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [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)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Membership Inference Attacks against Language Models via Neighbourhood Comparison](https://mlsanity.com/paper/2305.18462/) (2023)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)](https://mlsanity.com/paper/2406.17975/) (2024)
- [User Inference Attacks on Large Language Models](https://mlsanity.com/paper/2310.09266/) (2023)
- [Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment](https://mlsanity.com/paper/2302.10908/) (2023)
- [MoPe: Model Perturbation-based Privacy Attacks on Language Models](https://mlsanity.com/paper/2310.14369/) (2023)
- [A Survey on Privacy Risks and Protection in Large Language Models](https://mlsanity.com/paper/2505.01976/) (2025)
- [SensitiveNets: Learning Agnostic Representations with Application to Face Images](https://mlsanity.com/paper/1902.00334/) (2019)
- [Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics](https://mlsanity.com/paper/2402.09225/) (2024)
- [Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment](https://mlsanity.com/paper/2506.11880/) (2025)
- [Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigma](https://mlsanity.com/paper/2304.13680/) (2023)
- [PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)](https://mlsanity.com/paper/2507.02966/) (2025)
- [Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs](https://mlsanity.com/paper/2503.07384/) (2025)
- [Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairs](https://mlsanity.com/paper/2505.14699/) (2025)
- [EduEVAL-DB: A Role-Based Dataset for Pedagogical Risk Evaluation in Educational Explanations](https://mlsanity.com/paper/2602.15531/) (2026)
- [MINT-Demo: Membership Inference Test Demonstrator](https://mlsanity.com/paper/2503.08332/) (2025)
- [Ethical AI: Towards Defining a Collective Evaluation Framework](https://mlsanity.com/paper/2506.00233/) (2025)
- [Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning](https://mlsanity.com/paper/2509.07879/) (2025)

## Built on by (most cited first, 4 of 4)

- [Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering](https://mlsanity.com/paper/2607.07179/) (2026)
- [CrimeNER Demo: Named-Entity Recognition in the Crime Domain](https://mlsanity.com/paper/2607.14800/) (2026)
- [AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations](https://mlsanity.com/paper/2607.25634/) (2026)
- [inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs](https://mlsanity.com/paper/2610.18051/) (2026)

## Abstract (arXiv)

We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA). The primary goal is to assess whether individual samples were part of the training data of these adapted models, providing a useful auditing tool for the management of intellectual property and sensitive data. Our analysis explores the relationship between model perplexity and membership status, providing a systematic framework for estimating data exposure in fine-tuned LLMs. We conducted experiments on four models and three benchmark datasets, obtaining precision values in determining if given data were used for training ranging from 0.77 to 0.92, which outperform state-of-the-art baselines and demonstrate the robustness and generality of the proposed method. In general, our findings underscore the potential of LoRA-MINT as an effective and scalable framework for auditing LLMs, improving transparency, and fostering the ethical and responsible deployment of AI and NLP technologies. For the sake of concreteness and current relevance, our discussion and experiments are centered on LoRAadjusted LLMs, but note that most of the presented methodology is easily applicable for auditing training data given any other technique for adapting LLMs or, more generally, any other domain-adapted AI models.