论文标题
学习自然语言模型的用户实现差异隐私
User-Entity Differential Privacy in Learning Natural Language Models
论文作者
论文摘要
在本文中，我们介绍了一个新颖的用户实现差异隐私（UEDP）的概念，以在学习自然语言模型（NLMS）中的文本数据和数据所有者中同时提供正式的隐私保护。为了保存UEDP，我们开发了一种称为UEDP-ALG的新颖算法，以通过无缝结合用户和敏感实体抽样过程得出的紧密灵敏度优化了隐私损失和模型实用程序之间的权衡。广泛的理论分析和评估表明，使用基准数据集，我们的UEDP-ALG在几个NLM任务上在相同的隐私预算消耗下的模型实用程序中的基线方法优于模型实用程序的基线方法。
In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models (NLMs). To preserve UeDP, we developed a novel algorithm, called UeDP-Alg, optimizing the trade-off between privacy loss and model utility with a tight sensitivity bound derived from seamlessly combining user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.
