Autonomous Vehicles (AVs) represent a transformative advancement in modern transportation systems, offering significant improvements in operational efficiency and user experience. However, their widespread implementation faces critical security challenges, particularly regarding secure remote management during system failures or cyber-attacks. These vulnerabilities potentially compromise system integrity and undermine public confidence in autonomous technologies. We introduce a novel Internet of Autonomous Vehicles (IoAV) architecture integrating an AI-driven intrusion detection system with a Chaotic Map-Based Authenticated Key Agreement protocol to address these security concerns. This integration dynamically mitigates evolving security threats through adaptive system responses. Our framework incorporates Physical Unclonable Function (PUF) technology to generate cryptographically secure private keys, establishing robust communication channels between users, Charging Stations (CS), and AVs coordinated by an Electric Service Provider (ESP). Rigorous evaluation using the Real-or-Random (ROR) model demonstrates the protocol’s resilience against diverse attack vectors, including man-in-the-middle, replay, and adversarial attacks. Experimental validation confirms the framework’s effectiveness (97.8% detection accuracy, AUC-ROC: 0.976), computational efficiency (31.25% reduction in overhead, 4.2ms inference latency), and operational resilience (99.3% authentication integrity under $10^{3}$ requests/second DDoS simulation). The protocol achieves 51.38% reduced communication overhead compared to existing solutions, establishing our framework as demonstrably superior for IoAV security implementation within resource-constrained autonomous transportation infrastructures.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    AIDAS: AI-Enhanced Intrusion Detection and Authentication for Autonomous Vehicles


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    01.08.2025


    Format / Umfang :

    1745961 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SCHIFFAHRT - Reeder - Aidas Schwestern

    Frank, R. | Online Contents | 2001


    Cognitive Intrusion Detection System In Autonomous Vehicles Using Machine Learning

    Prabha, R Senthil / S, Gokula Krishnan / S, Kaushik et al. | IEEE | 2024


    IIDS: Intelligent Intrusion Detection System for Sustainable Development in Autonomous Vehicles

    Anbalagan, Sudha / Raja, Gunasekaran / Gurumoorthy, Sugeerthi et al. | IEEE | 2023


    BIOMETRIC AUTHENTICATION FOR CONNECTED VEHICLES INCLUDING AUTONOMOUS VEHICLES

    LOPEZ-HINOJOSA BRENNAN T / LOPEZ KERMIT D | Europäisches Patentamt | 2018

    Freier Zugriff

    Lightweight and Adaptive Data-Driven Intrusion Detection System for Autonomous Vehicles

    Aljabri, Wael / Hamid, Md. Abdul / Mosli, Rayan | IEEE | 2025