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 1504.00065cs.CRcs.DS
收藏

差分隐私中Laplace机制的最优性

Optimality of the Laplace Mechanism in Differential Privacy

Fragkiskos Koufogiannis, Shuo Han, George J. Pappas

摘要:

在高度互联的物联网领域,敏感信息的交换引起了严重的隐私问题。拉普拉斯机制--将拉普拉斯分布的人工噪声添加到敏感数据--是在差分隐私框架内提供隐私保证的广泛使用的方法之一。在这项工作中,我们提出了Lipschitz隐私,一个稍微严格的版本的差分隐私。我们证明了拉普拉斯机制是最佳的意义上,它最大限度地减少了均方误差的身份查询,提供隐私方面的$\ell_{1}$规范。除了尊重个人参与的$\ell_{1}$规范之外,我们还关注于提供高维数据隐私的$\ell_{2}$规范的使用。拉普拉斯机制的一个变化被证明具有最佳的均方误差从身份查询。最后,在个人提交高维敏感数据的情况下,最优机制的推导。

英文摘要:

In the highly interconnected realm of Internet of Things, exchange of sensitive information raises severe privacy concerns. The Laplace mechanism -- adding Laplace-distributed artificial noise to sensitive data -- is one of the widely used methods of providing privacy guarantees within the framework of differential privacy. In this work, we present Lipschitz privacy, a slightly tighter version of differential privacy. We prove that the Laplace mechanism is optimal in the sense that it minimizes the mean-squared error for identity queries which provide privacy with respect to the $\ell_{1}$-norm. In addition to the $\ell_{1}$-norm which respects individuals' participation, we focus on the use of the $\ell_{2}$-norm which provides privacy of high-dimensional data. A variation of the Laplace mechanism is proven to have the optimal mean-squared error from the identity query. Finally, the optimal mechanism for the scenario in which individuals submit their high-dimensional sensitive data is derived.

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。

↑