Fisher-Information Privacy

For privacy protection, the responses to the queries are systematically corrupted with an additive random noise. Using the Cramer-Rao bound, we can relate the variance of any estimator of the private database entries to the inverse of the trace of the Fisher information matrix, motivating its use as a measure of privacy. We can compute the probability density that minimizes the trace of the Fisher information (as a proxy for maximizing the measure of privacy) to find the optimal privacy-preserving policy.

Collaborators: Henrik Sandberg, Magnus Egerstedt

Funding: veski Victoria Fellowship, The University of Melbourne

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.