2012/02/15 by Liyue Fan, Li Xiong, Fan, Liyue +1
Computer Science · Medicine · #Data-Driven Disease Surveillance #Databases (cs.DB) #FOS: Computer and information sciences #Mobile Crowdsensing and Crowdsourcing #Privacy-Preserving Technologies in Data #cs.DB
paper · pdf · doi:10.48550/arxiv.1202.3461
openalex publication_date 2012/02/15 · arxiv created 2013/01/05 · arxiv updated 2013/01/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Sharing real-time aggregate statistics of private data is of great value to the public to perform data mining for understanding important phenomena, such as Influenza outbreaks and traffic congestion. However, releasing time-series data with standard differential privacy mechanism has limited utility due to high correlation between data values. We propose FAST, a novel framework to release real-time aggregate statistics under differential privacy based on filtering and adaptive sampling. To minimize the overall privacy cost, FAST adaptively samples long time-series according to the detected data dynamics. To improve the accuracy of data release per time stamp, FAST predicts data values at non-sampling points and corrects noisy observations at sampling points. Our experiments with real-world as well as synthetic data sets confirm that FAST improves the accuracy of released aggregates even under small privacy cost and can be used to enable a wide range of monitoring applications.