Imperial College London
Portrait Picture

ProfessorDenizGunduz

Faculty of Engineering, Department of Electrical and Electronic Engineering

Professor in Information Processing
 
 
 
//

Contact

 

+44 (0)20 7594 6218d.gunduz Website

 
 
//

Assistant

 

Ms Joan O'Brien +44 (0)20 7594 6316

 
//

Location

 

1016Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Erdemir:2020:10.1109/TIFS.2020.3013200,
author = {Erdemir, E and Dragotti, PL and Gunduz, D},
doi = {10.1109/TIFS.2020.3013200},
journal = {IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURIT},
pages = {389--401},
title = {Privacy-aware time-series data sharing with deep reinforcement learning},
url = {http://dx.doi.org/10.1109/TIFS.2020.3013200},
volume = {16},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Internet of things (IoT) devices are becoming increasingly popular thanks to many new services and applications they offer. However, in addition to their many benefits, they raise privacy concerns since they share fine-grained time-series user data with untrusted third parties. In this work, we study the privacy-utility trade-off (PUT) in time-series data sharing. Existing approaches to PUT mainly focus on a single data point; however, temporal correlations in time-series data introduce new challenges. Methods that preserve the privacy for the current time may leak significant amount of information at the trace level as the adversary can exploit temporal correlations in a trace. We consider sharing the distorted version of a user’s true data sequence with an untrusted third party. We measure the privacy leakage by the mutual information between the user’s true data sequence and shared version. We consider both the instantaneous and average distortion between the two sequences, under a given distortion measure, as the utility loss metric. To tackle the history-dependent mutual information minimization, we reformulate the problem as a Markov decision process (MDP), and solve it using asynchronous actor-critic deep reinforcement learning (RL). We evaluate the performance of the proposed solution in location trace privacy on both synthetic and GeoLife GPS trajectory datasets. For the latter, we show the validity of our solution by testing the privacy of the released location trajectory against an adversary network.
AU  - Erdemir,E
AU  - Dragotti,PL
AU  - Gunduz,D
DO  - 10.1109/TIFS.2020.3013200
EP  - 401
PY  - 2020///
SN  - 1556-6013
SP  - 389
TI  - Privacy-aware time-series data sharing with deep reinforcement learning
T2  - IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURIT
UR  - http://dx.doi.org/10.1109/TIFS.2020.3013200
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000559432500009&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://ieeexplore.ieee.org/document/9153837
UR  - http://hdl.handle.net/10044/1/82445
VL  - 16
ER  -
Download