TY - GEN
T1 - A rate-disortion perspective on local differential privacy
AU - Sarwate, Anand D.
AU - Sankar, Lalitha
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/1/30
Y1 - 2014/1/30
N2 - Local differential privacy is a model for privacy in which an untrusted statistician collects data from individuals who mask their data before revealing it. While randomized response has shown to be a good strategy when the statistician's goal is to estimate a parameter of the population, we consider instead the problem of locally private data publishing, in which the data collector must publish a version of the data it has collected. We model utility by a distortion measure and consider privacy mechanisms that act via a memoryless channnel operating on the data. If we consider a the source distribution to be unknown but in a class of distributions, we arrive at a robust-rate distortion model for the privacy-distortion tradeoff. We show that under Hamming distortions, the differential privacy risk is lower bounded for all nontrivial distortions, and that the lower bound grows logarithmically in the alphabet size.
AB - Local differential privacy is a model for privacy in which an untrusted statistician collects data from individuals who mask their data before revealing it. While randomized response has shown to be a good strategy when the statistician's goal is to estimate a parameter of the population, we consider instead the problem of locally private data publishing, in which the data collector must publish a version of the data it has collected. We model utility by a distortion measure and consider privacy mechanisms that act via a memoryless channnel operating on the data. If we consider a the source distribution to be unknown but in a class of distributions, we arrive at a robust-rate distortion model for the privacy-distortion tradeoff. We show that under Hamming distortions, the differential privacy risk is lower bounded for all nontrivial distortions, and that the lower bound grows logarithmically in the alphabet size.
UR - http://www.scopus.com/inward/record.url?scp=84946689176&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84946689176&partnerID=8YFLogxK
U2 - 10.1109/ALLERTON.2014.7028550
DO - 10.1109/ALLERTON.2014.7028550
M3 - Conference contribution
AN - SCOPUS:84946689176
T3 - 2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014
SP - 903
EP - 908
BT - 2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 52nd Annual Allerton Conference on Communication, Control, and Computing, Allerton 2014
Y2 - 30 September 2014 through 3 October 2014
ER -