Learning Differentially Private Mechanisms
Learning Differentially Private Mechanisms
复制标题
DOI：
10.1109/sp40001.2021.00060
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Subhajit Roy;Justin Hsu;Aws Albarghouthi
中科院分区：
文献类型：
--
作者：
Subhajit Roy;Justin Hsu;Aws Albarghouthi
差异隐私是对数据隐私的正式数学定义，它在学术界，工业和政府中引起了人们的关注。正确构建差异化私有算法的任务是不平凡的，并且在基础算法中犯了错误。当前，没有自动支持将现有的非私有程序转换为差异私有版本。在本文中，我们提出了一种技术，用于自动学习给定的非私人程序的准确且私密的版本。我们通过一系列技术来展示如何解决这个困难的程序综合问题：仔细选择代表性的示例输入，将问题减少到连续优化，并将结果映射回符号表达式。我们证明，我们的方法能够从差异隐私文献中学习基础算法，并显着优于自然程序合成基准。
Differential privacy is a formal, mathematical definition of data privacy that has gained traction in academia, industry, and government. The task of correctly constructing differentially private algorithms is non-trivial, and mistakes have been made in foundational algorithms. Currently, there is no automated support for converting an existing, non-private program into a differentially private version. In this paper, we propose a technique for automatically learning an accurate and differentially private version of a given non-private program. We show how to solve this difficult program synthesis problem via a combination of techniques: carefully picking representative example inputs, reducing the problem to continuous optimization, and mapping the results back to symbolic expressions. We demonstrate that our approach is able to learn foundational algorithms from the differential privacy literature and significantly outperforms natural program synthesis baselines.