# Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs

arXiv: https://arxiv.org/abs/2507.17259 · HTML: https://mlsanity.com/paper/2507.17259/

## Key facts

- Cited by 3 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 32 of its 47 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (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)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey](https://mlsanity.com/paper/2402.17944/) (2024)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [Tabular Representation, Noisy Operators, and Impacts on Table Structure Understanding Tasks in LLMs](https://mlsanity.com/paper/2310.10358/) (2023)
- [Exploring Memorization in Fine-tuned Language Models](https://mlsanity.com/paper/2310.06714/) (2023)
- [TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning](https://mlsanity.com/paper/2312.09039/) (2023)
- [TABLET: Learning From Instructions For Tabular Data](https://mlsanity.com/paper/2304.13188/) (2023)
- [NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization](https://mlsanity.com/paper/2406.17961/) (2024)
- [Optimizing Pretraining Data Mixtures with LLM-Estimated Utility](https://mlsanity.com/paper/2501.11747/) (2025)
- [Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models](https://mlsanity.com/paper/2312.12464/) (2023)
- [JarviX: A LLM No code Platform for Tabular Data Analysis and Optimization](https://mlsanity.com/paper/2312.02213/) (2023)

## Built on by (most cited first, 3 of 3)

- [Toward Reliable, Safe, and Secure LLMs for Scientific Applications](https://mlsanity.com/paper/2603.18235/) (2026)
- [Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries](https://mlsanity.com/paper/2606.26021/) (2026)
- [Probing Memorization of Tabular In-Context Learning](https://mlsanity.com/paper/2606.31208/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information (PII) in a highly structured and explicit format. As a result, privacy risks arise, since sensitive records can be inadvertently retained by the model and exposed through data extraction or membership inference attacks (MIAs). While existing MIA methods primarily target textual content, their efficacy and threat implications may differ when applied to structured data, due to its limited content, diverse data types, unique value distributions, and column-level semantics. In this paper, we present Tab-MIA, a benchmark dataset for evaluating MIAs on tabular data in LLMs and demonstrate how it can be used. Tab-MIA comprises five data collections, each represented in six different encoding formats. Using our Tab-MIA benchmark, we conduct the first evaluation of state-of-the-art MIA methods on LLMs finetuned with tabular data across multiple encoding formats. In the evaluation, we analyze the memorization behavior of pretrained LLMs on structured data derived from Wikipedia tables. Our findings show that LLMs memorize tabular data in ways that vary across encoding formats, making them susceptible to extraction via MIAs. Even when fine-tuned for as few as three epochs, models exhibit high vulnerability, with AUROC scores approaching 90% in most cases. Tab-MIA enables systematic evaluation of these risks and provides a foundation for developing privacy-preserving methods for tabular data in LLMs.