Protecting Global Properties of Datasets with Distribution Privacy Mechanisms
This work addresses confidentiality for aggregated dataset properties, which is an incremental step beyond individual record privacy in data protection.
The paper tackles the problem of protecting global dataset properties, such as trade secrets or demographic data, from inference attacks, by extending distribution privacy mechanisms like the Wasserstein and Gaussian Mechanisms. The results show these mechanisms reduce attack effectiveness while offering better utility than a group differential privacy baseline.
We consider the problem of ensuring confidentiality of dataset properties aggregated over many records of a dataset. Such properties can encode sensitive information, such as trade secrets or demographic data, while involving a notion of data protection different to the privacy of individual records typically discussed in the literature. In this work, we demonstrate how a distribution privacy framework can be applied to formalize such data confidentiality. We extend the Wasserstein Mechanism from Pufferfish privacy and the Gaussian Mechanism from attribute privacy to this framework, then analyze their underlying data assumptions and how they can be relaxed. We then empirically evaluate the privacy-utility tradeoffs of these mechanisms and apply them against a practical property inference attack which targets global properties of datasets. The results show that our mechanisms can indeed reduce the effectiveness of the attack while providing utility substantially greater than a crude group differential privacy baseline. Our work thus provides groundwork for theoretical mechanisms for protecting global properties of datasets along with their evaluation in practice.