5 papers
Pure-DP Statistical Query Release at the Conjectured Square-Root Rate
Jack Fitzsimons
Nikolov and Ullman asked whether k statistical queries on a universe of size T can be released under pure differential privacy with expected worst-coordinate error at the square-ro…
Better Privacy Guarantees for Larger Groups
Jack Fitzsimons
Pujol and Desfontaines asked whether a private histogram can allow more error on larger counts and use that slack to protect members of larger groups more strongly. We study this q…
Privacy in Theory, Bugs in Practice: Grey-Box Auditing of Differential Privacy Libraries
Tudor Cebere, David Erb, Damien Desfontaines +2
Differential privacy (DP) implementations are notoriously prone to errors, with subtle bugs frequently invalidating theoretical guarantees. Existing verification methods are often…
Private Means and the Curious Incident of the Free Lunch
Jack Fitzsimons, James Honaker, Michael Shoemate +1
We show that the most well-known and fundamental building blocks of DP implementations -- sum, mean, count (and many other linear queries) -- can be released with substantially red…
Naturally Private Recommendations with Determinantal Point Processes
Jack Fitzsimons, Agustín Freitas Pasqualini, Robert Pisarczyk +1
Often we consider machine learning models or statistical analysis methods which we endeavour to alter, by introducing a randomized mechanism, to make the model conform to a differe…