arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.09367cs.ITmath.IT
收藏

信息论隐私看门狗的性质及优化

On Properties and Optimization of Information-theoretic Privacy Watchdog

Parastoo Sadeghi, Ni Ding, Thierry Rakotoarivelo

摘要:

研究了数据共享中的隐私保护问题,其中$S$是需要保护的敏感变量,$X$是与$S$相关的非敏感有用变量.变量$X$随机分配到变量$Y$中,变量$Y$将根据$p_{Y|X}(y|x)$进行共享或发布。我们通过\emph{information privacy}(在文献中也称为\emph{log-lift})来测量隐私泄露,它保证了互信息隐私和差分隐私(DP)。令$\Xepsc \subseteq \X$包含$X$的字母表中的元素,其中对数提升的绝对值(简称为abs-log-lift)大于期望阈值$\eps$。当元素$x\in \Xepsc$被随机化为$y\in \Y$时,我们推导出跨结果对$(s,y)$的abs-log-lift的最佳上限。然后,我们证明了这个界限是通过\emph{$X$-invariant}随机化$p(y|x) = R(y)$为$x,y\in\Xepsc$。然而,由互信息$I(X;Y)$测量的效用在对abs-log-lift施加严格的上限$\eps$时严重受损。为了弥补这一点,并受到概率($\eps$,$δ$)-DP的启发,我们提出了一个宽松的($\eps$,$δ$)-日志升降机框架。为了实现这一放松,我们引入了一个贪婪的算法,免除随机化$\Xepsc$中的一些元素,只要他们的abs-log-lift是有界的$\eps$概率$1-δ$。数值结果表明,该算法在实现更好的隐私效用权衡的有效性。

英文摘要:

We study the problem of privacy preservation in data sharing, where $S$ is a sensitive variable to be protected and $X$ is a non-sensitive useful variable correlated with $S$. Variable $X$ is randomized into variable $Y$, which will be shared or released according to $p_{Y|X}(y|x)$. We measure privacy leakage by \emph{information privacy} (also known as \emph{log-lift} in the literature), which guarantees mutual information privacy and differential privacy (DP). Let $\Xepsc \subseteq \X$ contain elements n the alphabet of $X$ for which the absolute value of log-lift (abs-log-lift for short) is greater than a desired threshold $\eps$. When elements $x\in \Xepsc$ are randomized into $y\in \Y$, we derive the best upper bound on the abs-log-lift across the resultant pairs $(s,y)$. We then prove that this bound is achievable via an \emph{$X$-invariant} randomization $p(y|x) = R(y)$ for $x,y\in\Xepsc$. However, the utility measured by the mutual information $I(X;Y)$ is severely damaged in imposing a strict upper bound $\eps$ on the abs-log-lift. To remedy this and inspired by the probabilistic ($\eps$, $δ$)-DP, we propose a relaxed ($\eps$, $δ$)-log-lift framework. To achieve this relaxation, we introduce a greedy algorithm which exempts some elements in $\Xepsc$ from randomization, as long as their abs-log-lift is bounded by $\eps$ with probability $1-δ$. Numerical results demonstrate efficacy of this algorithm in achieving a better privacy-utility tradeoff.

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。

↑