Secure and Privacy-Preserving Data Management in Train Coupling/Decoupling Scenarios: A Comprehensive Review and Future Perspectives
Year: 2025
Type: article
Abstract: This paper systematically investigates the data privacy protection strategies in railway transportation systems, with a particular focus on the unique requirements of train coupling/decoupling scenarios. In such dynamic, distributed environments, existing passive security mechanisms and centralized architectures often fail to ensure secure data exchange and privacy preservation, particularly when computational resources are limited. To address these challenges, decentralized data-sharing technologies and privacy-preserving computation methods suitable for heterogeneous train networks were reviewed. Furthermore, we propose a blockchain-based asymmetric encrypted storage framework and a collaborative computing architecture based on federated learning, both tailored to the operational constraints of modern high-speed trains. Our approach integrates container virtualization, secure consensus protocols, and differential privacy techniques to enable traceable, tamper-proof, and privacy-aware data processing. Finally, this paper outlines future research directions concerning quantum-resistant security architectures and adaptive privacy mechanisms that can support the evolving needs of intelligent railway systems.
Source: Computing&AI Connect
Authors: Zhihang Zhang, Feng Wang, Peng Li
Institution: Beijing Jiaotong University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Award: G3278419361
OpenAlex ID: W4414542598