arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.14725cs.LGcs.CR
收藏

局部差分隐私对公平性影响的系统性与形式化研究:初步结果

A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results

INRIA(法国国家信息与自动化研究所);École Polytechnique(巴黎综合理工学院);IPP(IPP机构);Mathematical Institute of the Serbian Academy of Sciences and Arts(塞尔维亚科学院数学研究所);Inria Centre at the University Grenoble Alpes(格勒诺布尔大学Inria中心)

Karima Makhlouf, Tamara Stefanovic, Heber H. Arcolezi, Catuscia Palamidessi

AI总结:

本研究系统形式化地分析局部差分隐私对机器学习公平性的影响,给出基于联合分布和隐私水平的界限,并区分隐私减少或加剧歧视的情形,在合成与真实数据上初步验证。

摘要:

机器学习算法主要依赖于训练数据的可用性,并且根据领域的不同,这些数据可能包含数据提供者的敏感信息,从而导致显著的隐私问题。差分隐私是隐私保护机器学习的主要解决方案,而当服务器或数据收集者不被信任时,局部差分隐私模型是首选。近期的实验研究表明,局部差分隐私可能影响机器学习对不同个体子群体的预测,从而影响公平决策。然而,结果是相互矛盾的,因为一些研究显示隐私对公平性有积极影响,而另一些则显示消极影响。在这项工作中,我们对局部差分隐私对公平性的影响进行了系统性和形式化的研究。具体来说,我们进行了定量研究,考察在不同隐私水平和数据分布下,机器学习模型所做决策的公平性如何随局部差分隐私变化。特别是,我们提供了关于联合分布和隐私水平的界限,限定了局部差分隐私可能影响模型公平性的程度。我们刻画了隐私减少歧视的情况以及产生相反效果的情况。我们在合成数据集和真实世界数据集上验证了我们的理论发现。我们的结果是初步的,因为目前我们仅研究了一个敏感属性的情况,并且仅研究了统计差异、条件统计差异和平等机会差异。

英文摘要:

Machine learning (ML) algorithms rely primarily on the availability of training data, and, depending on the domain, these data may include sensitive information about the data providers, thus leading to significant privacy issues. Differential privacy (DP) is the predominant solution for privacy-preserving ML, and the local model of DP is the preferred choice when the server or the data collector are not trusted. Recent experimental studies have shown that local DP can impact ML prediction for different subgroups of individuals, thus affecting fair decision-making. However, the results are conflicting in the sense that some studies show a positive impact of privacy on fairness while others show a negative one. In this work, we conduct a systematic and formal study of the effect of local DP on fairness. Specifically, we perform a quantitative study of how the fairness of the decisions made by the ML model changes under local DP for different levels of privacy and data distributions. In particular, we provide bounds in terms of the joint distributions and the privacy level, delimiting the extent to which local DP can impact the fairness of the model. We characterize the cases in which privacy reduces discrimination and those with the opposite effect. We validate our theoretical findings on synthetic and real-world datasets. Our results are preliminary in the sense that, for now, we study only the case of one sensitive attribute, and only statistical disparity, conditional statistical disparity, and equal opportunity difference.

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。

↑