# Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4

arXiv: https://arxiv.org/abs/2404.05047 · HTML: https://mlsanity.com/paper/2404.05047/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 7 Apr 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- [DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models](https://mlsanity.com/paper/2310.20138/) (2023)
- [Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study](https://mlsanity.com/paper/1807.08379/) (2018)
- [Fairness Metrics: A Comparative Analysis](https://mlsanity.com/paper/2001.07864/) (2020)
- [Privately Fine-Tuning Large Language Models with Differential Privacy](https://mlsanity.com/paper/2210.15042/) (2022)
- [Adversarial Learning of Privacy-Preserving and Task-Oriented Representations](https://mlsanity.com/paper/1911.10143/) (2019)
- [Privacy Implications of Retrieval-Based Language Models](https://mlsanity.com/paper/2305.14888/) (2023)
- [Deep Private-Feature Extraction](https://mlsanity.com/paper/1802.03151/) (2018)
- [Learning Privacy Preserving Encodings through Adversarial Training](https://mlsanity.com/paper/1802.05214/) (2018)
- [Context-Aware Generative Adversarial Privacy](https://mlsanity.com/paper/1710.09549/) (2017)
- [MoPe: Model Perturbation-based Privacy Attacks on Language Models](https://mlsanity.com/paper/2310.14369/) (2023)
- [Active Privacy-utility Trade-off Against a Hypothesis Testing Adversary](https://mlsanity.com/paper/2102.08308/) (2021)
- [Uncertainty-Autoencoder-Based Privacy and Utility Preserving Data Type Conscious Transformation](https://mlsanity.com/paper/2205.01950/) (2022)
- [Distributed generation of privacy preserving data with user customization](https://mlsanity.com/paper/1904.09415/) (2019)

## Built on by (most cited first, 2 of 2)

- [HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection](https://mlsanity.com/paper/2408.02927/) (2024)
- [Zero-Shot Learning for Obsolescence Risk Forecasting](https://mlsanity.com/paper/2506.21240/) (2025)

## Abstract (arXiv)

We investigate the application of large language models (LLMs), specifically GPT-4, to scenarios involving the tradeoff between privacy and utility in tabular data. Our approach entails prompting GPT-4 by transforming tabular data points into textual format, followed by the inclusion of precise sanitization instructions in a zero-shot manner. The primary objective is to sanitize the tabular data in such a way that it hinders existing machine learning models from accurately inferring private features while allowing models to accurately infer utility-related attributes. We explore various sanitization instructions. Notably, we discover that this relatively simple approach yields performance comparable to more complex adversarial optimization methods used for managing privacy-utility tradeoffs. Furthermore, while the prompts successfully obscure private features from the detection capabilities of existing machine learning models, we observe that this obscuration alone does not necessarily meet a range of fairness metrics. Nevertheless, our research indicates the potential effectiveness of LLMs in adhering to these fairness metrics, with some of our experimental results aligning with those achieved by well-established adversarial optimization techniques.