Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Theory and Practice of Differential Privacy

Differential Privacy for Black-Box Statistical Analyses

Nitin Kohli · Paul Laskowski


Abstract:

We formalize a notion of a privacy wrapper, defined as an algorithm that can take an arbitrary and untrusted script and produce an output with differential privacy guarantees. Our novel privacy wrapper design leverages subsets of data and halts to overcome the issue of unknowable sensitivity.

Chat is not available.