arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.08413cs.LGcs.CRcs.CY
收藏

决策树中的隐私约束公平性估计

Privacy Constrained Fairness Estimation for Decision Trees

Department of Information and Computing Sciences, Utrecht(乌得勒支信息与计算科学系);Responsible AI Team, Dutch Central Government Audit Service(荷兰中央政府审计服务责任AI团队)

Florian van der Steen, Fré Vink, Heysem Kaya

AI总结:

本文研究了在决策树中结合差分隐私的公平性估计问题,提出了一种隐私感知的规则公平性估计方法,通过实验和理论分析证明该方法在可解释性较高的决策树上表现更优。

摘要:

随着敏感数据价值的增加,其保护变得愈加重要。此外,监管机构和社会对模型开发者要求其人工智能模型非歧视性的压力也在增加。同时,对于高风险任务,需要可解释和透明的人工智能模型。一般来说,测量任何人工智能模型的公平性需要数据集中个体的敏感属性,从而引发隐私问题。在本文中,进一步探讨了公平性、隐私和可解释性之间的权衡。我们特别研究了带有差分隐私的决策树(DTs)的统计平性(SP)。我们提出了一种新的方法,称为隐私感知的规则公平性估计(PAFER),该方法可以在差分隐私意识下估计决策树的SP。差分隐私利用第三方法律实体安全持有敏感数据,通过向敏感数据添加噪声来保证隐私。我们实验性地比较了几种差分隐私机制。我们显示,使用拉普拉斯机制,该方法能够以低误差估计SP,同时以高确定性保护数据集中个体的隐私。我们进一步通过实验和理论证明,该方法在人类通常认为更容易解释的决策树上表现更好。

英文摘要:

The protection of sensitive data becomes more vital, as data increases in value and potency. Furthermore, the pressure increases from regulators and society on model developers to make their Artificial Intelligence (AI) models non-discriminatory. To boot, there is a need for interpretable, transparent AI models for high-stakes tasks. In general, measuring the fairness of any AI model requires the sensitive attributes of the individuals in the dataset, thus raising privacy concerns. In this work, the trade-offs between fairness, privacy and interpretability are further explored. We specifically examine the Statistical Parity (SP) of Decision Trees (DTs) with Differential Privacy (DP), that are each popular methods in their respective subfield. We propose a novel method, dubbed Privacy-Aware Fairness Estimation of Rules (PAFER), that can estimate SP in a DP-aware manner for DTs. DP, making use of a third-party legal entity that securely holds this sensitive data, guarantees privacy by adding noise to the sensitive data. We experimentally compare several DP mechanisms. We show that using the Laplacian mechanism, the method is able to estimate SP with low error while guaranteeing the privacy of the individuals in the dataset with high certainty. We further show experimentally and theoretically that the method performs better for DTs that humans generally find easier to interpret.

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。

↑