The previous system is driverless machines that take appropriate recommendations in all situations. They have transformed the conveyor system. The operations rely on sensed information and simulated knowledge to understand and reach conclusions concerning transportation operation, and to accommodate to improving circumstances. The method protection happens in three steps. Before the strikes occur, associated companies and businesses require determining class of advances that are liable to occur and their moderation practices. When the crimes occur, the operation should observe the complete CAV, and recognize initiatives. After raids follow, the method should respond to crimes appropriately and be capable to retrieve from seizures. The recommended UML‐based CAV cyber protection structure is produced to determine the connections among each element and the construction in the CAV. Confined information has couple of sources. They contain device and software knowledge in the CAV frame. They have the running status info of appliance and programs. The Hardware section is the detector info obtained from the carrier enclosing by several CAV sensing devices. The program group has limited information assembled by the programs in CAVs. The surface course comprises information collected from other items. As each object has its own ID saved in its restricted knowledge, the visible details need this learning to support the testimony of the evidence source. After recognizing the transmitted ID, communications are classified into either individual stating that information is governed properly. The carriers or foundations need to transfer hidden knowledge. It can be obtained by distinct users and collected in the safe location. The generalized category stocks information that everyone could obtain. The knowledge processing course has four essential data computation methodologies. The generating component accumulates knowledge from various origins. These datasets need to be formatted, organized and combined for computation. The Processing group computes the information, including cleaning or annotating the data for analysis. The Verification class includes components that make sure the data are secure, fulfilling the cyber security requirements of the CAV system. The recommended system has additional databases to take of the different kinds of assaults in the system. The reliability is increased by 7.32% and time taken to overcome an attack is decreased by 11.59% compared to the previous one.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Reliable Machine Learning‐Based Detection for Cyber Security Attacks on Connected and Autonomous Vehicles


    Beteiligte:
    Rawat, Romil (Herausgeber:in) / Sowjanya, A. Mary (Herausgeber:in) / Patel, Syed Imran (Herausgeber:in) / Jaiswal, Varshali (Herausgeber:in) / Khan, Imran (Herausgeber:in) / Balaram, Allam (Herausgeber:in) / Ambika, N. (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    19.12.2022


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Hardware-Based Cyber Security for Connected Vehicles

    Harrison, Lee / Pickford, James | British Library Conference Proceedings | 2023


    A Survey on Cyber-Security of Connected and Autonomous Vehicles (CAVs)

    Sun, Xiaoqiang / Yu, F. Richard / Zhang, Peng | IEEE | 2022


    Hardware-Based Cyber Security for Connected Vehicles

    Pickford, James / Harrison, Lee | SAE Technical Papers | 2023


    Cyber security analysis of connected vehicles

    Mwanje, Maria Drolence / Kaiwartya, Omprakash / Aljaidi, Mohammad et al. | Wiley | 2024

    Freier Zugriff