A location semantic privacy protection model based on spatial influence.

The utilization of numerous location-based intelligent services yields massive traffic trajectory data. Mining such data unveils internal and external user features, offering significant application value across various domains. Nonetheless, while trajectory data mining enhances user convenience, it also exposes their privacy to potential breaches. To address the problem that existing traffic trajectory privacy protection methods rarely consider the location semantics and the spatial influence of interest points when constructing k-anonymity sets, which makes user trajectories vulnerable to attacks, a Location Semantic Privacy Protection Model based on Spatial Influence (LSPPM-SI) is proposed to resist semantic attacks. Firstly, a location semantic mining algorithm is proposed to classify the stopovers based on positional semantics, thereby simplifying the semantic information contained in user trajectories. Secondly, a diversified semantic dummy location selecting algorithm is proposed to resist semantic attacks. To enhance the availability of traffic trajectory data while safeguarding location semantics, a Hilbert curves is used to reduce the area of anonymous regions, and a diversified semantic anonymous set is constructed. Thirdly, the spatial influence of interest points is defined and used to verify the rationality of dummy trajectories within the anonymous trajectory set, thereby preventing attackers from identifying dummy trajectories. Finally, the problem of synthesizing dummy trajectories is transformed into a matching problem for directed bipartite graphs and the optimal k-anonymity set is obtained using the Kuhn Munkres algorithm. Experimental results demonstrate that the proposed model improves traffic trajectory data availability and semantic protection performance by 14% and 46.5%, respectively, compared to traditional models.