分类数据的产生差分隐私:概念及其在机器学习中的应用
Production of Categorical Data Verifying Differential Privacy: Conception and Applications to Machine Learning
摘要:
私人和公共组织定期收集和分析有关其同事,志愿者,客户等的数字化数据,但是,由于大多数个人数据是敏感的,在设计隐私保护系统方面存在关键挑战。为了解决隐私问题,研究团体提出了不同的方法来保护隐私,差分隐私(DP)作为一个正式的定义,允许量化的隐私效用权衡。此外,使用本地DP(LDP)模型,用户可以在将其数据传输到服务器之前在本地对其进行清理。因此,本论文的目标是双重的:O $_1$)为了提高LDP保证下的多个频率估计的实用性和隐私性,这是统计学习的基础。和O $_2$)评估在差异隐私数据上训练的机器学习(ML)模型的隐私-效用权衡。对于O $_1$,我们首先从两个“多”角度解决问题,即,多个属性和多个集合,同时专注于实用性。其次,我们把注意力集中在多属性方面,我们提出了一个解决方案,侧重于隐私,同时保持效用。在这两种情况下,我们通过分析和实验验证证明了我们提出的解决方案的优势,在国家的最先进的LDP协议。对于O $_2$,我们根据经验评估了旨在解决现实问题同时确保DP保证的基于ML的解决方案。事实上,我们主要使用了来自隐私保护ML文献的输入数据扰动设置。在这种情况下,整个数据集都是独立清理的,因此,我们从集中式数据所有者的角度实现了LDP算法。在所有情况下,我们得出的结论是,差异私有ML模型实现了与非私有ML模型几乎相同的效用指标。
英文摘要:
Private and public organizations regularly collect and analyze digitalized data about their associates, volunteers, clients, etc. However, because most personal data are sensitive, there is a key challenge in designing privacy-preserving systems. To tackle privacy concerns, research communities have proposed different methods to preserve privacy, with Differential privacy (DP) standing out as a formal definition that allows quantifying the privacy-utility trade-off. Besides, with the local DP (LDP) model, users can sanitize their data locally before transmitting it to the server. The objective of this thesis is thus two-fold: O$_1$) To improve the utility and privacy in multiple frequency estimates under LDP guarantees, which is fundamental to statistical learning. And O$_2$) To assess the privacy-utility trade-off of machine learning (ML) models trained over differentially private data. For O$_1$, we first tackled the problem from two "multiple" perspectives, i.e., multiple attributes and multiple collections throughout time, while focusing on utility. Secondly, we focused our attention on the multiple attributes aspect only, in which we proposed a solution focusing on privacy while preserving utility. In both cases, we demonstrate through analytical and experimental validations the advantages of our proposed solutions over state-of-the-art LDP protocols. For O$_2$, we empirically evaluated ML-based solutions designed to solve real-world problems while ensuring DP guarantees. Indeed, we mainly used the input data perturbation setting from the privacy-preserving ML literature. This is the situation in which the whole dataset is sanitized independently and, thus, we implemented LDP algorithms from the perspective of the centralized data owner. In all cases, we concluded that differentially private ML models achieve nearly the same utility metrics as non-private ones.
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。