arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.12580cs.LGcs.CR
收藏

基于过拟合检测的合成数据成员推断攻击

Membership Inference Attacks against Synthetic Data through Overfitting Detection

University of Cambridge(剑桥大学);Alan Turing Institute(艾伦·图灵研究所)

Boris van Breugel, Hao Sun, Zhaozhi Qian, Mihaela van der Schaar

摘要:

数据是大多数科学的基础。不幸的是,共享数据可能会受到侵犯数据隐私的风险的阻碍,从而阻碍医疗保健等领域的研究。合成数据是一种潜在的解决方案。它旨在生成与原始数据具有相同分布的数据,但不会泄露有关个人的信息。成员推断攻击(Membership Inference Attack,MIA)是一种常见的隐私攻击,攻击者试图确定特定的真实样本是否用于模型的训练。以前提出MIA反对生成模型的作品要么表现出低性能-给人一种数据高度私密的错觉-或者需要假设访问内部生成模型参数-这是一种风险相对较低的情况,因为数据发布者通常只发布合成数据,而不是模型。在这项工作中,我们认为一个现实的MIA设置,假设攻击者有一些知识的底层数据分布。我们提出了DOMIAS,一个基于密度的MIA模型,旨在通过生成模型的局部过拟合来推断成员资格。实验表明,DOMIAS是显着更成功的MIA比以前的工作,特别是在攻击不常见的样品。后者令人不安,因为这些样本可能对应于代表性不足的群体。我们还演示了DOMIAS的MIA性能评分如何为隐私提供可解释的度量,为数据发布者提供了一种新的工具,用于在其合成数据中实现所需的隐私-效用权衡。

英文摘要:

Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a potential solution. It aims to generate data that has the same distribution as the original data, but that does not disclose information about individuals. Membership Inference Attacks (MIAs) are a common privacy attack, in which the attacker attempts to determine whether a particular real sample was used for training of the model. Previous works that propose MIAs against generative models either display low performance -- giving the false impression that data is highly private -- or need to assume access to internal generative model parameters -- a relatively low-risk scenario, as the data publisher often only releases synthetic data, not the model. In this work we argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model. Experimentally we show that DOMIAS is significantly more successful at MIA than previous work, especially at attacking uncommon samples. The latter is disconcerting since these samples may correspond to underrepresented groups. We also demonstrate how DOMIAS' MIA performance score provides an interpretable metric for privacy, giving data publishers a new tool for achieving the desired privacy-utility trade-off in their synthetic data.

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。

↑