Algorithms with More Granular Differential Privacy Guarantees
This work addresses privacy concerns in data analysis and learning tasks by providing more granular privacy guarantees, though it appears incremental as it builds on existing differential privacy frameworks.
The paper tackles the problem of applying differential privacy with overly large privacy parameters by introducing partial differential privacy, which quantifies privacy on a per-attribute basis, and designs algorithms that achieve smaller per-attribute privacy parameters than possible for entire records.
Differential privacy is often applied with a privacy parameter that is larger than the theory suggests is ideal; various informal justifications for tolerating large privacy parameters have been proposed. In this work, we consider partial differential privacy (DP), which allows quantifying the privacy guarantee on a per-attribute basis. In this framework, we study several basic data analysis and learning tasks, and design algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person (i.e., all the attributes).