Understanding Compressive Adversarial Privacy
Understanding Compressive Adversarial Privacy
复制标题
DOI：
10.1109/cdc.2018.8619455
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Xiao Chen;P. Kairouz;R. Rajagopal
中科院分区：
文献类型：
--
作者：
Xiao Chen;P. Kairouz;R. Rajagopal
在不牺牲太多隐私的情况下设计数据共享机制可以被认为是数据持有者和恶意攻击者之间的游戏。本文描述了一个压缩对抗隐私框架，捕获数据隐私和效用之间的权衡。在假设数据保持器和攻击者只能使用线性变换修改数据的情况下，通过凸优化刻画了最优数据发布机制.然后，我们建立了一个更现实的数据发布机制，可以依赖于一个非线性压缩模型，而攻击者使用神经网络。我们在一系列的实证应用中证明，这个框架，包括压缩对抗隐私，可以保护敏感信息。
Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off between the data privacy and utility. We characterize the optimal data releasing mechanism through convex optimization when assuming that both the data holder and attacker can only modify the data using linear transformations. We then build a more realistic data releasing mechanism that can rely on a nonlinear compression model while the attacker uses a neural network. We demonstrate in a series of empirical applications that this framework, consisting of compressive adversarial privacy, can preserve sensitive information.