Re:2020 Knuth Prize is awarded to Cynthia Dwork [pdf]
by janhenr on Tuesday May 12, 2020 @02:17PM
(#23157581)
Check out Han Song's (MIT, most well-known for NN compression) Lab new paper on gradient leaking and follow-up work. https://arxiv.org/abs/1906.08935
I attended a talk by him recently and was very impressed by the work of his lab in this area.
So the main question I have is let's say I'm working with sensitive data like emails or doctors notes. How can I train an ML model that would still learn something useful without leaking private data.
When I say "leak", an example would be I train an RNN on some company data email data and when I feed the RNN "$AMZN" the network would say SELL.
How can I quantify how much the model has learnt and how much privacy has been leaked.