IEEE Transactions on Intelligent Transportation Systems · 2022 · 15 citations · 22 references
ComputingComputer ScienceCybersecurityComputer SecurityMessage PassingNetwork SecurityCryptographic AlgorithmsPrivacy-preserving ProtocolsSecure Mobile CommunicationSecurity SystemsVehicle CybersecurityVehicle-to-everything CommunicationBelief PropagationLocalization Accuracy AnalysisLocalization In Vehicular NetworksMan-in-the-middle Attack MitigationMessage AggregationSecurity In Vehicular NetworksVariational Message PassingVehicle-to-everything Communication Security
Various attacks in communication network threaten the security of vehicular system. For cooperative location-sensing system, man-in-the-middle attack and eavesdropping attack would lead to catastrophic collapse of vehicular network localization. In this paper, we propose a federated cryptosystem localization based on optimized constraints. In the localization phase, a message passing algorithm combining belief propagation (BP) and variational message passing (VMP) is derived by defining penalty function, which can detect the distance outliers. The messages generated by each vehicular node or base station are encrypted with Paillier cryptosystem. Because Paillier cryptosystem is featured by homomorphic addition, message aggregation reduces large amount of decryption. The localization messages finally work in a federated transmission scheme for privacy preserving against man-in-the-middle attack and eavesdropping attack. In terms of localization accuracy, algorithm parameters, convergence analysis and efficiency, simulation results show that cybersecurity of cooperative localization is proved to be effective in various scenarios of vehicular network.
22
Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach
Yi Liu, James J. Q. Yu, Jiawen Kang et al. · IEEE Internet of Things Journal · 2020 · 678 citations · Full text