PCDP-CRLPPM: a classified regional location privacy-protection model based on personalized clustering with differential privacy in data management.

The article focuses on the development of a novel location privacy protection model named Classified Regional Location Privacy-Protection Model based on Personalized Clustering with Differential Privacy (PCDP-CRLPPM) to address privacy and utility challenges in transportation big data management. PCDP-CRLPPM employs a twice-clustering algorithm combined with grid division to create personalized regions of interest (PROIs) tailored to users' privacy needs, classifies these regions based on spatiotemporal features, and adaptively allocates privacy budgets using a Sensitive-priority Algorithm (SpA). The model adds Laplacian noise to cluster centroids via a Regional-fuzzy algorithm to defend against two specific attacks: Reverse-clustering Inference (RC-I) and Mobile-spatiotemporal Feature Inference (MSF-I). Experimental evaluations on real-world datasets demonstrate that PCDP-CRLPPM achieves a superior balance between privacy protection and data utility compared to existing methods, with ablation studies confirming the effectiveness of its personalized clustering and adaptive budget allocation components.