ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing

Mobile edge crowdsensing enables large-scale real-time sensing services, but its continuous data collection and transmission pipeline exposes terminal devices to dynamic privacy risks. Existing privacy protection schemes in MECS typically rely on static configurations or coarse-grained adaptation, making them difficult to balance privacy, data utility, and device overhead under changing channel conditions, data sensitivity, and resource availability.

To address this problem, we propose ALPINE, a lightweight closed-loop framework for adaptive privacy budget allocation in MECS. ALPINE performs multi-dimensional risk perception on terminal devices by jointly modeling channel, semantic, contextual, and resource risks, and maps the resulting risk state to a privacy budget through an offline-trained TD3 policy. The selected budget is then used to drive local differential privacy perturbation before data transmission, while edge-side privacy-utility evaluation provides feedback for policy switching and periodic refinement.

In this way, ALPINE forms a terminal-edge collaborative control loop that enables real-time, risk-adaptive privacy protection with low online overhead. Extensive experiments on multiple real-world datasets show that ALPINE achieves a better privacy-utility trade-off than representative baselines, reduces the effectiveness of membership inference, property inference, and reconstruction attacks, and preserves robust downstream task performance under dynamic risk conditions. Prototype deployment further demonstrates that ALPINE introduces only modest runtime overhead on resource-constrained devices.

Comments on the paper include that it is 12 pages long, with 12 figures and 6 tables, and has been submitted to The International Conference on Web Services. The paper is categorized under Machine Learning, and can be cited as arXiv:2510.17162, with a DOI of https://doi.org/10.48550/arXiv.2510.17162. The submission history of the paper shows that it was first submitted on October 20, 2025, and a revised version was submitted on April 9, 2026.