Privacy Preservation in a Two-Tiered Sensor Network through Correlation Tracking

Abstract

The architecture of two tiered sensor networks, where storage nodes serve as an intermediate tier between sensors and a sink for storing and processing data, has aroused researchers' attention because of the benefits of power and storage saving. In a sensor network, multiple sensor data streams are correlated. Correlation tracking can describe the key trends and reduce the complexity of further data processing. However, the importance of storage nodes also makes them attractive to attackers. In this paper we propose a method to guarantee both the utility and privacy of data on storage nodes through correlation tracking. To preserve privacy, we add random noise on original data. To preserve utility, the additive noise is distributed along the direction of sensor data. We provide both a mathematical and experimental evaluation on real dataset to validate the effectiveness of our algorithm.