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 1001.2767cs.CRcs.DBcs.DS
收藏

Minimax Agent的普遍最优隐私机制

Universally Optimal Privacy Mechanisms for Minimax Agents

Mangesh Gupte, Mukund Sundararajan

摘要:

发布敏感数据的聚合信息的方案必须解决信息消费者的效用和数据库参与者的隐私之间的权衡。差分隐私是一个完善的隐私定义--这是一个针对所有攻击者的通用保证,无论他们的侧信息或意图如何。在本文中,我们提出了一个通用的治疗效用的基础上,从决策理论的标准极大极小规则(相对于效用模型,这是贝叶斯)。在我们的模型中,信息消费者是极大极小(风险厌恶)代理,每个拥有一些查询的边信息,每个赋予一个损失函数模型的容忍不准确。此外,信息消费者是理性的,因为他们积极地将来自机制的信息与他们的辅助信息以最小化损失的方式结合起来。在这种理性行为的假设下,我们证明了对于每个固定计数的查询,一定的几何机制是普遍最优的所有极大极小信息消费者。此外,我们的解决方案使得有可能在多个级别的隐私在一个抗共谋的方式发布查询结果。

英文摘要:

A scheme that publishes aggregate information about sensitive data must resolve the trade-off between utility to information consumers and privacy of the database participants. Differential privacy is a well-established definition of privacy--this is a universal guarantee against all attackers, whatever their side-information or intent. In this paper, we present a universal treatment of utility based on the standard minimax rule from decision theory (in contrast to the utility model in, which is Bayesian). In our model, information consumers are minimax (risk-averse) agents, each possessing some side-information about the query, and each endowed with a loss-function which models their tolerance to inaccuracies. Further, information consumers are rational in the sense that they actively combine information from the mechanism with their side-information in a way that minimizes their loss. Under this assumption of rational behavior, we show that for every fixed count query, a certain geometric mechanism is universally optimal for all minimax information consumers. Additionally, our solution makes it possible to release query results at multiple levels of privacy in a collusion-resistant manner.

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。

↑