Reinforcement-Learning-Based Query Optimization in Differentially Private IoT Data Publishing

With the advancement of Internet of Things (IoT) and computing paradigms, massive data are collected and processed to enhance intelligent applications. However, by deliberately sending some queries, an attacker may be able to derive the sensitive information of IoT data owners. To prevent privacy leakage during IoT data query, differential privacy (DP) hides private information by introducing noise to the query results. As DP introduces randomized noise that will affect query accuracy (data utility), the tradeoff between privacy preservation and data utility is a challenge. In this article, we first propose a novel optimization framework for single query to minimize the privacy cost, while satisfying both personalized DP and customized data utility. We design a reinforcement learning-based algorithm for single query optimization framework (SQOF_RL) to solve the optimization problem efficiently. Then, we propose a SQOF_RL and SVT-based batch query optimization mechanism (S2BQOM) to answer more queries privately. The performance evaluation shows that SQOF_RL and S(2)BQOM can effectively optimize single query and batch queries in terms of privacy cost, data utility, personalized privacy, and query satisfaction. Finally, the performance analysis reveals that our work can be applied to multiple linear/nonlinear query functions instead of one particular query function.

Automated summary

This article introduces a novel optimization framework for single query to minimize privacy cost while ensuring personalized DP and customized data utility. By introducing a reinforcement learning-based algorithm, the optimization problem can be efficiently solved to enhance the tradeoff between privacy preservation and data utility.