TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data

TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
复制标题

TAPAS:用于合成数据的对抗性隐私审计的工具箱

DOI:
10.48550/arxiv.2211.06550
复制
发表时间:
2022
期刊:
ArXiv
影响因子:
--
通讯作者:
L. Szpruch
L. Szpruch
中科院分区:
--
文献类型:
--
作者:
F. Houssiau;James Jordon;Samuel N. Cohen;Owen Daniel;Andrew Elliott;James Geddes;C. Mole;Camila Rangel Smith;L. Szpruch

文献摘要

参考文献

被引文献

相似文献

大规模收集个人数据有望改善决策并加速创新。然而,共享和使用这些数据引发了严重的隐私问题。一个有希望的解决方案是产生合成数据,人工记录来共享,而不是真实的数据。由于合成记录与真人无关,这直观地防止了经典的重新识别攻击。然而,这不足以保护隐私。我们在这里介绍TAPAS,这是一个攻击工具箱,用于评估各种场景下的合成数据隐私。这些攻击包括对先前作品的概括和新的攻击。我们还介绍了一个用于推断合成数据隐私威胁的通用框架,并通过几个示例展示了TAPAS。
Personal data collected at scale promises to improve decision-making and accelerate innovation. However, sharing and using such data raises serious privacy concerns. A promising solution is to produce synthetic data, artificial records to share instead of real data. Since synthetic records are not linked to real persons, this intuitively prevents classical re-identification attacks. However, this is insufficient to protect privacy. We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios. These attacks include generalizations of prior works and novel attacks. We also introduce a general framework for reasoning about privacy threats to synthetic data and showcase TAPAS on several examples.
DOI: --
发表时间: 2019-01
期刊: ArXiv
影响因子: --
作者:
Ryan McKenna;D. Sheldon;G. Miklau
通讯作者: Ryan McKenna;D. Sheldon;G. Miklau
DOI: --
发表时间: 2020-06
期刊: ArXiv
影响因子: --
作者:
Matthew Jagielski;Jonathan Ullman;Alina Oprea
通讯作者: Matthew Jagielski;Jonathan Ullman;Alina Oprea