arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.05047cs.LGcs.CR
收藏

利用GPT-4对表格数据中的零样本隐私效用权衡进行初步探索

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

Kansas State University(堪萨斯州立大学);Louisiana State University(路易斯安那州立大学)

Bishwas Mandal, George Amariucai, Shuangqing Wei

AI总结:

本研究探索GPT-4以零样本文本提示方式处理表格数据隐私-效用权衡,发现该简单方法性能可媲美复杂对抗优化方法,且在公平性指标上展现出潜在有效性。

摘要:

我们研究了大语言模型(LLMs),具体为GPT-4,在涉及表格数据隐私与效用权衡场景中的应用。我们的方法通过将表格数据点转换为文本格式来提示GPT-4,随后以零样本方式加入精确的清理指令。主要目标是对表格数据进行清理,使其阻碍现有机器学习模型准确推断隐私特征,同时允许模型准确推断与效用相关的属性。我们探索了多种清理指令。值得注意的是,我们发现这种相对简单的方法所产生的性能,与用于管理隐私-效用权衡的更复杂的对抗性优化方法相当。此外,尽管提示成功地从现有机器学习模型的检测能力中隐藏了隐私特征,但我们观察到,仅这种隐藏并不一定能满足一系列公平性指标。尽管如此,我们的研究表明LLMs在遵守这些公平性指标方面具有潜在有效性,我们的部分实验结果与成熟的对抗性优化技术所取得的结果一致。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑