Ordinal Data Stream Collection with Condensed Local Differential Privacy

Continuous collection of users' ordinal data is essential to numerous industrial applications, such as disease surveillance, road traffic analysis, and computation offloading. However, the data collector is not fully-trusted, so that the necessitate privacy protection on the sensitive ordinate data streams of users becomes critical. Local Differential Privacy (LDP) is typically used to resolve this problem with high efficiency for real-time data analysis. However, existing LDP methods are mainly designed for one-time data collection, and they bring low utility in some time slots for continuous collection, due to the data sparsity problem that some users' data are empty in most of time slots. Therefore, we propose a Condensed LDP (CLDP)-based scheme, which provides real-time statistics with the protection of each user's time-series data and the high utility in each time slot. First, our scheme optimizes the utility by allocating each user's privacy budget in the time dimension. The privacy budgets originally used in empty time slots are saved and allocated to non-empty time slots for every user, so as to increase the utility in each time slot. Then, CLDP is used to further counteract the negative impact of data sparsity. Finally, privacy analysis is given to show the privacy protection of data streams, and sufficient experiments on real datasets are conducted to demonstrate the effectiveness of the proposed scheme.