arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2310.06258cs.CR
收藏

利用参与者效用函数比较差分隐私的不同版本

Using Participants' Utility Functions to Compare Versions of Differential Privacy

Nitin Kohli, Michael Carl Tschantz

AI总结:

该研究从潜在研究参与者视角出发,结合决策理论与测量理论,通过个体效用函数和欧几里得度量比较差分隐私变体,发现效用函数性质及ε、δ取值会显著影响隐私保障的偏好选择。

摘要:

我们采用决策理论,从潜在研究参与者的视角比较差分隐私的各类变体。我们假设研究参与者可能承受的所有潜在后果集合上存在一种偏好排序,从而能够对个体效用函数展开分析。借助测量理论,我们提出应通过经典欧几里得度量来衡量期望效用的变化。随后我们探讨了在不同决策场景下,哪些隐私保障对个体更具吸引力的问题。通过分析我们发现,潜在参与者效用函数的性质,以及ε和δ的具体取值,会极大地改变哪种隐私保障更优的结论。

英文摘要:

We use decision theory to compare variants of differential privacy from the perspective of prospective study participants. We posit the existence of a preference ordering on the set of potential consequences that study participants can incur, which enables the analysis of individual utility functions. Drawing upon the theory of measurement, we argue that changes in expected utilities should be measured via the classic Euclidean metric. We then consider the question of which privacy guarantees would be more appealing for individuals under different decision settings. Through our analysis, we found that the nature of the potential participant's utility function, along with the specific values of $ε$ and $δ$, can greatly alter which privacy guarantees are preferable.

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。

↑