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

arXiv:2404.05047v1 Announce Type: new
Abstract: 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 …

abstract application arxiv cs.cr cs.lg data exploration format gpt gpt-4 inclusion language language models large language large language models llms privacy prompting tabular tabular data textual type utility zero-shot