arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.08784cs.CR
收藏

针对差分隐私拉普拉斯机制的成员参考攻击

Membership Reference Attack against Laplace Mechanism of Differential Privacy

Sichuan University(四川大学);University of Electronic Science and Technology of China(电子科技大学)

Wen Huang

AI总结:

针对差分隐私拉普拉斯机制,利用线性查询的线性性质构造成员参考攻击,通过获取独立同分布样本并进行假设检验判断目标记录是否在数据集中。

摘要:

差分隐私是一种广泛接受的隐私保护概念,拉普拉斯机制是处理数值数据的差分隐私机制的著名实例。在本文中,我们指出差分隐私没有考虑查询的线性性质,导致信息泄露。为了展示信息泄露,我们构造了一种针对拉普拉斯机制的成员参考攻击。具体地,我们提出了一种在拉普拉斯机制约束下获取线性查询答案的多个独立同分布样本的方法。该方法基于线性查询的线性性质和一些背景知识。基于获得的样本,使用假设检验方法判断目标记录是否在数据集中。

英文摘要:

The differential privacy is a widely accepted conception of privacy protection and the Laplace mechanism is a famous instance of differential privacy mechanisms to deal with numerical data. In this paper, we point out that the differential privacy does not take liner property of queries into account, resulting in information leakage. In order to show the information leakage, we construct a membership reference attacks against the Laplace mechanism. Concretely, we propose a method to obtain multiple independent identical distribution samples of linear query's answer under constrains of the Laplace mechanism. The proposed method is based on linear property of linear query and some background knowledge. Based on obtained samples, a hypothesis test method is used to determine whether a targert record is in data set.

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。

↑