Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Theory and Practice of Differential Privacy

A bounded-noise mechanism for differential privacy

Yuval Dagan · Gil Kur


Abstract:

We present an asymptotically optimal (epsilon, δ)-private mechanism for answering multiple, adaptively asked, ∆-sensitive queries, settling the conjecture of Steinke and Ullman [2020]. Our algorithm adds independent noise of bounded magnitude to each query, while prior solutions relied on unbounded noise such as the Laplace and Gaussian mechanisms.

Chat is not available.