arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02818cs.LGcs.CR
收藏

变分泄漏:信息复杂性在隐私泄漏中的作用

Variational Leakage: The Role of Information Complexity in Privacy Leakage

University of Geneva(日内瓦大学);Imperial College London(帝国理工学院)

Amir Ahooye Atashin, Behrooz Razeghi, Deniz Gündüz, Slava Voloshynovskiy

摘要:

我们研究了信息复杂性的作用,在隐私泄漏的属性的对手的利益,这是不知道先验的系统设计者。考虑到有监督的表示学习设置,并使用神经网络来参数化信息量的变化范围,我们研究了以下因素对信息泄漏量的影响:信息复杂度正则化子权重、潜在空间维数、已知效用和未知敏感属性集的基数、效用与敏感属性之间的相关性,以及对对手利益的敏感属性的潜在偏见。我们在有色MNIST和CelebA数据集上进行了广泛的实验,以评估信息复杂性对内在泄漏量的影响。

英文摘要:

We study the role of information complexity in privacy leakage about an attribute of an adversary's interest, which is not known a priori to the system designer. Considering the supervised representation learning setup and using neural networks to parameterize the variational bounds of information quantities, we study the impact of the following factors on the amount of information leakage: information complexity regularizer weight, latent space dimension, the cardinalities of the known utility and unknown sensitive attribute sets, the correlation between utility and sensitive attributes, and a potential bias in a sensitive attribute of adversary's interest. We conduct extensive experiments on Colored-MNIST and CelebA datasets to evaluate the effect of information complexity on the amount of intrinsic leakage.

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。

↑