Subhajit Roy, Justin Hsu, Aws Albarghouthi
{"title":"Learning Differentially Private Mechanisms","authors":"Subhajit Roy, Justin Hsu, Aws Albarghouthi","doi":"10.1109/SP40001.2021.00060","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":6786,"journal":{"name":"2021 IEEE Symposium on Security and Privacy (SP)","volume":"238 1","pages":"852-865"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Symposium on Security and Privacy (SP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SP40001.2021.00060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

摘要

差分隐私是数据隐私的一种正式的数学定义,在学术界、工业界和政府中得到了广泛的关注。正确构造差分私有算法是一项艰巨的任务,在基础算法中已经出现了一些错误。目前,没有自动支持将现有的非私有程序转换为不同的私有版本。在本文中,我们提出了一种自动学习给定非私有程序的准确和差异私有版本的技术。我们展示了如何通过技术组合来解决这个困难的程序合成问题:仔细挑选有代表性的示例输入,将问题简化为持续优化,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分隐私文献中学习基本算法,并且显著优于自然程序合成基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Learning Differentially Private Mechanisms
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信