一种面向本地差分隐私时间序列聚合的后处理可验证回退方法及系统
By using a sliding window budget allocation and hybrid trust fusion mechanism, combined with adaptive triggers and post-processing strength determination, the problem of insufficient stability of post-processing schemes in existing technologies in mobile crowd sensing and urban IoT systems is solved. This enables online verifiable rollback and privacy protection, and improves the robustness and availability of the system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YANTAI UNIV
- Filing Date
- 2026-03-27
- Publication Date
- 2026-07-17
AI Technical Summary
In online continuous publishing environments for mobile crowd sensing and urban IoT, existing post-processing solutions struggle to effectively safeguard and verify post-processing results online without relying on round-by-round real values, resulting in insufficient system stability, uncontrollable risks, and a lack of interpretability.
It employs a sliding window budget allocation, sensitivity control, and hybrid trust fusion mechanism, combined with adaptive triggers and post-processing strength determination. Through dual-path routing scheduling and robust aggregation, it generates verifiable rollback certificates, providing online verification and rollback basis to ensure privacy protection and result stability.
It enables online safeguarding and verifiable rollback of post-processing results without relying on round-by-round true values, improving the robustness and deployability of the system, reducing the impact of noise, and enhancing the stability and usability of the aggregation results.
Smart Images
Figure CN121940755B_ABST