Adaptively Sharing Time-Series with Differential Privacy

Details Adaptively Sharing Time-Series with Differential Privacy Adaptively Sharing Time-Series with Differential Privacy

2012-02-15

arxiv.org/abs/1202.3461v1

Computer Science

Databases

Scientific paper

Sharing real-time aggregate statistics of private data has given much benefit to the public to perform data mining for understanding important phenomena, such as Influenza outbreaks and traffic congestions. We propose an adaptive approach with sampling and estimation to release aggregated time series under differential privacy, the key innovation of which is that we utilize feedback loops based on observed (perturbed) values to dynamically adjust the estimation model as well as the sampling rate. To minimize the overall privacy cost, our solution uses the PID controller to adaptively sample long time-series according to detected data dynamics. To improve the accuracy of data release per timestamp, the Kalman filter is used to predict data values at non-sampling points and to estimate true values from perturbed query answers at sampling points. Our experiments with three real data sets show that it is beneficial to incorporate feedback into both the estimation model and the sampling process. The results confirmed that our adaptive approach improves accuracy of time-series release and has excellent performance even under very small privacy cost.

Affiliated with

Also associated with

No associations

Rating

Adaptively Sharing Time-Series with Differential Privacy does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Adaptively Sharing Time-Series with Differential Privacy, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptively Sharing Time-Series with Differential Privacy will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-124708