Continuous release of temporal correlation location statistics with local differential privacy

The continuous release of location statistics plays a significant role in various real-world applications, such as traffic management and customization of public services. However, existing literature primarily focuses on static scenarios or perturbing locations at a single timestamp, disregarding the consideration of temporal correlation in mobile users. This oversight leaves the data susceptible to privacy attacks, including inference attacks, resulting in extra privacy leakage. To address this challenge, we propose a Local Differential Privacy Budget Distribution and Streaming Data Releasing (LPBD) mechanism for real-world location datasets. Specifically, we investigate the problem of continuously releasing location statistics for infinite streams while protecting user privacy and quantify the impact of temporal correlation on privacy leakage. The LPBD is a novel w-event level privacy-preserving mechanism, which has the capability to provide an adequate privacy budget for each timestamp and effectively mitigate the privacy leakage problem resulting from temporal correlation. Experimental results demonstrate that LPBD enhances data availability with strong privacy guarantees compared to state-of-the-art baseline methods.