Towards Secure and Efficient Data Scheduling for Vehicular Social Networks

TL;DR

This work tackles secure and efficient data scheduling in highly dynamic vehicular social networks by proposing DSQL, a learning-based framework that couples Q-learning for routing decisions with a six-layer MLP for rapid data processing and differential privacy for protecting rewards and actions. The Q-learning component updates a Q-table to select next-hop nodes, while the MLP accelerates decision making, and differential privacy protects sensitive information from inference attacks. Extensive simulations on Veins/SUMO with KITTI and NuScenes data show that DSQL outperforms competitive baselines across accuracy, travel cost, connectivity, delay, and security metrics, demonstrating its potential for real-time, privacy-preserving data exchange in V2X/IoV scenarios. The results underscore the method’s practical impact for secure, low-latency vehicular communications and point to future enhancements such as abnormal driving behavior detection and blockchain-based privacy protections.

Abstract

Efficient data transmission scheduling within vehicular environments poses a significant challenge due to the high mobility of such networks. Contemporary research predominantly centers on crafting cooperative scheduling algorithms tailored for vehicular networks. Notwithstanding, the intricacies of orchestrating scheduling in vehicular social networks both effectively and efficiently remain formidable. This paper introduces an innovative learning-based algorithm for scheduling data transmission that prioritizes efficiency and security within vehicular social networks. The algorithm first uses a specifically constructed neural network to enhance data processing capabilities. After this, it incorporates a Q-learning paradigm during the data transmission phase to optimize the information exchange, the privacy of which is safeguarded by differential privacy through the communication process. Comparative experiments demonstrate the superior performance of the proposed Q-learning enhanced scheduling algorithm relative to existing state-of-the-art scheduling algorithms in the context of vehicular social networks.

Figures (14)

• Figure 1: System model.
• Figure 2: An Overview of the proposed DSQL algorithm.
• Figure 3: Q-learning-based data computation.
• Figure 4: Multi-layer perceptron model.
• Figure 5: Activation Function for Different Data Processing Range.