ALPINE: A Lightweight and Adaptive Privacy-Decision Agent Framework for Dynamic Edge Crowdsensing

2025-10-20

AI Summary

In mobile edge crowdsensing (MECS), static differential privacy (DP) mechanisms struggle to simultaneously ensure strong privacy guarantees, high data utility, and low energy consumption under dynamic, resource-constrained conditions. To address this, we propose a lightweight adaptive DP framework featuring a closed-loop control architecture. Its core innovation is a privacy decision agent based on Twin-Delayed Deep Deterministic Policy Gradient (TD3), which integrates dynamic risk assessment and edge-coordinated verification to enable real-time, on-device adaptation of privacy budgets. Theoretical analysis and realistic-simulation experiments demonstrate that the framework significantly enhances robustness against inference attacks while preserving data utility and energy efficiency. Crucially, it achieves fine-grained, low-overhead dynamic privacy calibration—making it highly suitable for large-scale edge crowdsourcing applications.

Technology Category

• Machine Learning: Privacy
• Multiagent Systems: Mechanism Design
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Security and Privacy: Privacy-enhancing technologies
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Mobile edge crowdsensing (MECS) systems continuously generate and transmit user data in dynamic, resource-constrained environments, exposing users to significant privacy threats. In practice, many privacy-preserving mechanisms build on differential privacy (DP). However, static DP mechanisms often fail to adapt to evolving risks, for example, shifts in adversarial capabilities, resource constraints and task requirements, resulting in either excessive noise or inadequate protection. To address this challenge, we propose ALPINE, a lightweight, adaptive framework that empowers terminal devices to autonomously adjust differential privacy levels in real time. ALPINE operates as a closed-loop control system consisting of four modules: dynamic risk perception, privacy decision via twin delayed deep deterministic policy gradient (TD3), local privacy execution and performance verification from edge nodes. Based on environmental risk assessments, we design a reward function that balances privacy gains, data utility and energy cost, guiding the TD3 agent to adaptively tune noise magnitude across diverse risk scenarios and achieve a dynamic equilibrium among privacy, utility and cost. Both the collaborative risk model and pretrained TD3-based agent are designed for low-overhead deployment. Extensive theoretical analysis and real-world simulations demonstrate that ALPINE effectively mitigates inference attacks while preserving utility and cost, making it practical for large-scale edge applications.

Problem

• Adapting differential privacy to dynamic edge environments with evolving risks
• Balancing privacy protection with data utility and energy constraints
• Providing lightweight autonomous privacy decisions for resource-limited edge devices

Innovation

• Adaptive differential privacy framework for edge devices
• Closed-loop control with TD3-based autonomous noise adjustment
• Balances privacy, utility, and cost via lightweight risk model