Timezone: »

 
Poster
Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate
James Jordon · Jinsung Yoon · Mihaela van der Schaar

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #89
in Applications -- Privacy, Anonymity, and Security »

Differential Privacy is a popular and well-studied notion of privacy. In the era ofbig data that we are in, privacy concerns are becoming ever more prevalent and thusdifferential privacy is being turned to as one such solution. A popular method forensuring differential privacy of a classifier is known as subsample-and-aggregate,in which the dataset is divided into distinct chunks and a model is learned on eachchunk, after which it is aggregated. This approach allows for easy analysis of themodel on the data and thus differential privacy can be easily applied. In this paper,we extend this approach by dividing the data several times (rather than just once)and learning models on each chunk within each division. The first benefit of thisapproach is the natural improvement of utility by aggregating models trained ona more diverse range of subsets of the data (as demonstrated by the well-knownbagging technique). The second benefit is that, through analysis that we provide inthe paper, we can derive tighter differential privacy guarantees when several queriesare made to this mechanism. In order to derive these guarantees, we introducethe upwards and downwards moments accountants and derive bounds for thesemoments accountants in a data-driven fashion. We demonstrate the improvementsour model makes over standard subsample-and-aggregate in two datasets (HeartFailure (private) and UCI Adult (public)).

Keywords: Classification · Privacy, Anonymity, and Security · Applications · Algorithms
[ Paper]  [ Poster] 

Author Information

James Jordon (University of Oxford)
Jinsung Yoon (University of California, Los Angeles)

I am a research scientist at Google Cloud AI. I am currently working on diverse machine learning research topics such as generative models, self- and semi-supervised learning, model interpretation, data imputation, and synthetic data generation. Previously, I worked on machine learning for medicine with Professor Mihaela van der Schaar as a graduate student researcher in UCLA Electrical and Computer Engineering Department. I received my Ph.D. and M.S. in Electrical and Computer Engineering Department at UCLA, and B.S. in Electrical and Computer Engineering at Seoul National University (SNU).

Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)

More from the Same Authors