Information hierarchy studied for differential privacy filters and odometers
Original title: An Information Hierarchy of Privacy Filters and Odometers
Moving up the information hierarchy yields unbounded utility advantages for privacy filters and arbitrary precision improvements for odometers.
The research classifies privacy filters and odometers by levels of information used: spec-level, mechanism-level, and realisation-level. Strict separations in performance are established across these levels. Randomisation provides orthogonal improvements at every level.
- Unbounded utility advantage for filters with richer information
- Arbitrary large improvement in precision for odometers
- Randomisation yields utility improvements orthogonal to information
- Classes are distinct with no performance loss
- Performance governed by information access and randomisation
From the original article
1 min read at arxiv.orgIn sequential data analysis, privacy loss accumulates over time, and privacy filters and odometers are used to control and track this cumulative cost. We study how the information used by differential privacy filters and odometers fundamentally limits what they can achieve.
By Sophie Taylor · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.