QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems
QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems
复制标题
QuerySnout：自动发现针对基于查询的系统的属性推断攻击
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Y. de Montjoye
中科院分区：
文献类型：
--
作者：
Ana;F. Houssiau;Antoine Cully;Y. de Montjoye
虽然基于查询的系统（QBS）已成为匿名共享数据的主要解决方案之一，但构建能够强大保护数据集贡献者隐私的QBS是一个难题。依赖于差分隐私保证的理论解决方案很难以合理的准确性正确实现，而临时解决方案可能包含未知的漏洞。因此，评估QBS提供的隐私必须通过评估各种隐私攻击的准确性来完成。然而，针对QBS的现有攻击需要时间和专业知识来开发，需要针对受攻击的特定系统进行手动定制，并且范围有限。在本文中，我们开发了QuerySnout，第一种自动发现基于查询的系统中的漏洞的方法。QuerySnout将目标记录和QBS作为黑盒作为输入，分析其在一个或多个数据集上的行为，并输出多组查询以及一条规则，以联合收割机组合它们的答案，以揭示目标记录的敏感属性。QuerySnout使用基于新的突变算子的进化搜索技术来找到容易导致攻击的多组查询，并使用机器学习分类器从所选查询的答案中推断敏感属性。我们通过将其应用于两种攻击场景（假设访问私有数据集或来自同一分发的不同数据集），三个真实世界的数据集和各种保护机制来展示QuerySnout的多功能性。我们发现QuerySnout的攻击始终等同于或优于，有时是一个很大的差距，从文献中最好的攻击。最后，我们展示了如何QuerySnout可以扩展到QBS，需要一个预算，并应用QuerySnout到一个简单的QBS的基础上的拉普拉斯机制。总之，我们的研究结果表明，自动化系统已经可以发现针对QBS的强大而准确的攻击，从而可以“按下按钮”自动测试高度复杂的QBS。我们相信，这一系列的研究对于在理论和实践中提高提供隐私保护访问个人数据的系统的鲁棒性至关重要。
Although query-based systems (QBS) have become one of the main solutions to share data anonymously, building QBSes that robustly protect the privacy of individuals contributing to the dataset is a hard problem. Theoretical solutions relying on differential privacy guarantees are difficult to implement correctly with reasonable accuracy, while ad-hoc solutions might contain unknown vulnerabilities. Evaluating the privacy provided by QBSes must thus be done by evaluating the accuracy of a wide range of privacy attacks. However, existing attacks against QBSes require time and expertise to develop, need to be manually tailored to the specific systems attacked, and are limited in scope. In this paper, we develop QuerySnout, the first method to automatically discover vulnerabilities in query-based systems. QuerySnout takes as input a target record and the QBS as a black box, analyzes its behavior on one or more datasets, and outputs a multiset of queries together with a rule to combine answers to them in order to reveal the sensitive attribute of the target record. QuerySnout uses evolutionary search techniques based on a novel mutation operator to find a multiset of queries susceptible to lead to an attack, and a machine learning classifier to infer the sensitive attribute from answers to the queries selected. We showcase the versatility of QuerySnout by applying it to two attack scenarios (assuming access to either the private dataset or to a different dataset from the same distribution), three real-world datasets, and a variety of protection mechanisms. We show the attacks found by QuerySnout to consistently equate or outperform, sometimes by a large margin, the best attacks from the literature. We finally show how QuerySnout can be extended to QBSes that require a budget, and apply QuerySnout to a simple QBS based on the Laplace mechanism. Taken together, our results show how powerful and accurate attacks against QBSes can already be found by an automated system, allowing for highly complex QBSes to be automatically tested "at the pressing of a button". We believe this line of research to be crucial to improve the robustness of systems providing privacy-preserving access to personal data in theory and in practice.
登录
查看更多内容
DOI：
--
发表时间：
2020-06
期刊：
ArXiv
影响因子：
--
作者：
Matthew Jagielski;Jonathan Ullman;Alina Oprea
通讯作者：
Matthew Jagielski;Jonathan Ullman;Alina Oprea
DOI：
--
发表时间：
2018-06
期刊：
--
影响因子：
--
作者：
H. Dai;Hui Li-;Tian Tian-Tian;Xin Huang;L. Wang;Jun Zhu;Le Song
通讯作者：
H. Dai;Hui Li-;Tian Tian-Tian;Xin Huang;L. Wang;Jun Zhu;Le Song
DOI：
10.1109/bigdata47090.2019.9006389
发表时间：
2019-12
期刊：
2019 IEEE International Conference on Big Data (Big Data)
影响因子：
--
作者：
A. Oehmichen;Shubham Jain;Andrea Gadotti;Yves-Alexandre de Montjoye
通讯作者：
A. Oehmichen;Shubham Jain;Andrea Gadotti;Yves-Alexandre de Montjoye
当信号处于噪声中时：利用 Diffix 的粘性噪声
DOI：
--
发表时间：
2019
期刊：
--
影响因子：
--
作者：
Gadotti A
通讯作者：
Gadotti A