Connected and Autonomous Vehicles (CAVs) provide significant societal benefits but pose serious security risks due to their high connectivity and openness. Traditional security measures like cryptography and intrusion detection systems (IDSs) are reactive and passive, posing significant challenges to securing CAVs. We propose a proactive and collaborative threat-sharing framework to tackle the above challenges and enhance CAV security through vehicular honeypots. The proposed framework leverages federated learning, which allows CAVs to share threat information decentralized while preserving their privacy. Additionally, we design an optimal incentive mechanism that considers three private information of CAVs, including deployment, training, and communication costs. Specifically, we leverage the self-disclosure property of the contract theory, which can effectively address information asymmetry and incentive mismatches between CAVs and the IDS server, motivating CAVs to participate in threat sharing. Finally, through a series of simu- lation experiments, we validate the feasibility of the contract and evaluate the effectiveness of our proposed incentive mechanism.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Federated Learning based Vehicular Threat Sharing: A Multi-Dimensional Contract Incentive Approach


    Contributors:
    He, Chao (author) / Luan, Tom H. (author) / Cheng, Nan (author) / Wei, Guiyi (author) / Su, Zhou (author) / Liu, Yiliang (author)


    Publication date :

    2023-10-10


    Size :

    1177200 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Contract Theory Based Incentive Mechanism for Clustered Vehicular Federated Learning

    Wang, Siyang / Zhao, Haitao / Wen, Wanli et al. | IEEE | 2024


    Incentive Based Federated Learning Data Dissemination for Vehicular Edge Computing Networks

    Bute, Muhammad Saleh / Fan, Pingzhi / Luo, Quyuan | IEEE | 2023


    Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach

    Lim, Wei Yang Bryan / Huang, Jianqiang / Xiong, Zehui et al. | IEEE | 2021