4 papers
PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
Hilal Asi, Vitaly Feldman, Hannah Keller +2
We revisit the problem of secure aggregation of high-dimensional vectors in a two-server system such as Prio. These systems are typically used to aggregate vectors such as gradient…
Distributed Differentially Private Data Analytics via Secure Sketching
Jakob Burkhardt, Hannah Keller, Claudio Orlandi +1
We introduce the linear-transformation model, a distributed model of differentially private data analysis. Clients have access to a trusted platform capable of applying a public ma…
Differentially Private Selection from Secure Distributed Computing
Ivan Damgård, Hannah Keller, Boel Nelson +2
Given a collection of vectors , the selection problem asks to report the index of an "approximately largest" entry in .…
Quantifying identifiability to choose and audit in differentially private deep learning
Daniel Bernau, Günther Eibl, Philip W. Grassal +2
Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists mus…