Achieving Transparency Report Privacy in Linear Time

Achieving Transparency Report Privacy in Linear Time
复制标题

在线性时间内实现透明度报告隐私

DOI:
10.1145/3460001
复制
发表时间:
2022
期刊:
Journal of Data and Information Quality
影响因子:
--
通讯作者:
Pal, Ranjan
Pal, Ranjan
中科院分区:
--
文献类型:
--
作者:
Chen, Chien-Lun;Golubchik, Leana;Pal, Ranjan

文献摘要

参考文献

相似文献

一份可问责的算法透明度报告(ATR)应彻底调查(a)底层算法的合法性,以及(B)算法决策的公平性,同时保护数据主体的隐私。然而,一个可证明的正式研究的影响,数据主体的隐私所造成的效用发布ATR(调查透明度和公平性),尚未在文献中得到解决。这种研究的牵强的好处在于公开发布ATR的隐私-效用权衡的系统特征,以及它们对社会,政治和经济维度的相应应用特定影响。在本文中,我们首先调查和展示所带来的潜在的隐私危害部署的透明度和公平措施在发布的ATR。为了保护数据主体的隐私,然后我们提出了一个线性时间最优隐私计划,建立在标准线性分式规划(LFP)理论,宣布ATR,受约束控制的隐私扰动的效用的透明度计划的容忍度。随后,我们量化的隐私效用的权衡所引起的我们的计划,并分析隐私扰动的公平性措施的ATR的影响。据我们所知,这是第一个同时解决隐私、效用和公平三者之间权衡的分析工作,适用于算法透明度报告。
An accountablealgorithmic transparency report (ATR)shouldideallyinvestigate (a)transparencyof the underlying algorithm, and (b)fairnessof the algorithmic decisions, and at the same time preserve data subjects’privacy. However, a provably formal study of the impact to data subjects’ privacy caused by the utility of releasing an ATR (that investigates transparency and fairness), has yet to be addressed in the literature. The far-fetched benefit of such a study lies in the methodical characterization of privacy-utility trade-offs for release of ATRs in public, and their consequential application-specific impact on the dimensions of society, politics, and economics. In this paper, we first investigate and demonstrate potential privacy hazards brought on by the deployment of transparency and fairness measures in released ATRs.To preserve data subjects’ privacy, we then propose a linear-time optimal-privacy scheme, built upon standardlinear fractional programming (LFP)theory, for announcing ATRs, subject to constraints controlling the tolerance of privacy perturbation on the utility of transparency schemes. Subsequently, we quantify the privacy-utility trade-offs induced by our scheme, and analyze the impact of privacy perturbation on fairness measures in ATRs. To the best of our knowledge, this is the first analytical work that simultaneously addresses trade-offs between the triad of privacy, utility, and fairness, applicable to algorithmic transparency reports.
数学毁灭性武器:大数据如何加剧不平等
DOI: --
发表时间: 2019
期刊:
影响因子: --
作者:
T. Democracy;Cathy O’Neil;Harris Mateen
通讯作者: Harris Mateen
DOI: 10.1145/3287560.3287577
发表时间: 2019-01
期刊: Proceedings of the Conference on Fairness, Accountability, and Transparency
影响因子: --
作者:
Meg Young;Luke Rodriguez;Emilyann Keller;Feiyang Sun;Boyang Sa;Jan Whittington;Bill Howe
通讯作者: Meg Young;Luke Rodriguez;Emilyann Keller;Feiyang Sun;Boyang Sa;Jan Whittington;Bill Howe
高等教育中的种族和民族代表性
DOI: --
发表时间: 2020
期刊:
影响因子: --
作者:
Tomás E. Monarrez;Kelia Washington
通讯作者: Kelia Washington
所有人的隐私:确保公平公正的隐私保护
DOI: --
发表时间: 2018
期刊: Accountability and Transparency
影响因子: --
作者:
Ekstrand, Michael D.;Joshaghani, Rezvan;Mehrpouyan, Hoda
通讯作者: Mehrpouyan, Hoda
DOI: --
发表时间: 2013
影响因子: 2.7
作者:
F. Kamiran;Indrė Žliobaitė;T. Calders
通讯作者: T. Calders