יום ראשון, 6.1.2019, 10:30
It is no secret that online companies, hospitals, credit-card companies
and governments hold massive datasets composed of our sensitive personal
details. Information from such datasets is often released using some
privacy preserving heuristics, which have been repeatedly shown to fail.
That is why in recent years the notion of differential privacy has been
gaining much attention, as an approach for conducting data-analysis that
adheres to a strong and mathematically rigorous notion of privacy.
Indeed, many differentially private analogs of existing data-analysis
techniques have already been devised. These are, however, new
algorithms, that require the use of additional random noise on top of
In this talk we will demonstrate how existing techniques, that were
developed independently of any privacy consideration, preserve
differential privacy by themselves --- when parameters are properly set.
The main focus of the talk will be the Johnson-Lindenstrauss Transform,
which preserves differential privacy provided the input satisfies some
``well spread'' properties. We will discuss applications of this
algorithm in approximating multiple linear regressions and in
statistical inference. Moreover, focusing on linear regression, we will
exhibit additional techniques that preserve privacy: regularization,
addition of random datapoints and Bayesian sampling.
(Time permitting, we will survey a very different technique, de-noising
neural networks, that also aligns with the definition of differential
privacy in the local model.)
The talk is self-contained and no prior knowledge is assumed.
Or Sheffet is currently an assistant professor at the Department of
Computing Science at the University of Alberta as well as a PI at the
Alberta Machine Intelligence Institute (AMII). He received his B.Sc. in
math and CS from the Hebrew University and his M.Sc from the Weizmann
Institute of Science. He got a PhD in CS from Carnegie Mellon
University, advised by Prof. Avrim Blum, where his work deals with the
intersection of machine learning, privacy and theory. After his PhD he
was a research fellow at the Simon's Institute for the Theory of
Computing at UC Berkeley, did a post-doctoral fellowship at Harvard
University's School of Engineering and Applied Sciences as a member of
the "Privacy-Tools for Sharing Research Data" project, and was a
visiting scholar at Department of Math and Statistics at the University