Privacy-Preserving Large-Scale AI Models for Intelligent Railway Transportation Systems:Hierarchical Poisoning Attacks and Defenses in Federated Learning

The development of Intelligent Railway Transportation Systems necessitates incorporating privacy-preserving mechanisms into AI models to protect sensitive information and enhance system efficiency.Federated learning offers a promising solution by allowing multiple clients to train models collaboratively without sharing private data.However,despite its privacy benefits,federated learning systems are vulnerable to poisoning attacks,where adversaries alter local model parameters on compromised clients and send malicious updates to the server,potentially compromising the global model’s accuracy.In this study,we introduce PMM(Perturbation coefficient Multiplied by Maximum value),a new poisoning attack method that perturbs model updates layer by layer,demonstrating the threat of poisoning attacks faced by federated learning.Extensive experiments across three distinct datasets have demonstrated PMM’s ability to significantly reduce the global model’s accuracy.Additionally,we propose an effective defense method,namely CLBL(Cluster Layer By Layer).Experiment results on three datasets have confirmed CLBL’s effectiveness.

System architecture and basic platform for intelligent high-speed railway

Purpose-This paper aims to provide top-level design and basic platform for intelligent application in China high-speed railway.Design/methodology/approach-Based on the analysis for the future development trends of world railway,combined with the actual development needs in China high-speed railway,The definition and scientific connotation of intelligent high-speed railway(IHSR)are given at first,and then the system architecture of IHSR are outlined,including 1 basic platform,3 business sectors,10 business fields,and 18 innovative applications.At last,a basic platform with cloud edge integration for IHSR is designed.Findings-The rationality,feasibility and implementability of the system architecture of IHSR have been verified on and applied to the Beijing-Zhangjiakou high-speed railway,providing important support for the construction and operation of the world’s first IHSR.Originality/value-This paper systematically gives the definition and connotation of the IHSR and put forward the system architecture of IHSR for first time.It will play the most important role in the design,construction and operation of IHSR.

Ethernet Implementation of Fault Tolerant Train Network for Entertainment and Mixed Control Traffic

This paper studies the integration of the control system and entertainment on board of train wagons. Both the control and entertainment loads are implemented on top of Gigabit Ethernet, each with a dedicated controller/server. The control load has mixed sampling periods. It is proven that this system can tolerate the failure of one controller in one wagon. In a two wagon scenario, fault tolerance at the controller level is studied, and simulation results show that the system can tolerate the failure of 3 controllers. The system is successful in meeting the packet end-to-end delay with zero packet loss in all OPNET simulated scenarios. The maximum permissible entertainment load is determined for the fault tolerant scenarios.

Optimal control and energy storage for DC electric train systems using evolutionary algorithms

Electrified railways are becoming a popular transport medium and these consume a large amount of electrical energy.Environmental concerns demand reduction in energy use and peak power demand of railway systems.Furthermore,high transmission losses in DC railway systems make local storage of energy an increasingly attractive option.An optimisation framework based on genetic algorithms is developed to optimise a DC electric rail network in terms of a comprehensive set of decision variables including storage size,charge/discharge power limits,timetable and train driving style/trajectory to maximise benefits of energy storage in reducing railway peak power and energy consumption.Experimental results for the considered real-world networks show a reduction of energy consumption in the range 15%–30%depending on the train driving style,and reduced power peaks.