Scholarlink

<p>Threat Analysis and Risk Assessment (TARA) methodologies aid in the early detection of potential threats during the concept and design phases of automotive security engineering process. Their importance is underscored by the relevant industry standards such ISO/SAE 21434 and SAE J3061. While human expertise and involvement are vital for conducting effective TARA, Artificial Intelligence (AI) can enhance the process significantly by automating certain aspects and thus streamlining operations. This study introduces an AI-driven approach to enhance the implementation of TARA. The proposed method leverages machine learning and evolutionary computing algorithms to identify cybersecurity threats in Connected and Autonomous Vehicles (CAVs) through the STRIDE framework. A structured and preprocessed dataset, containing various threat scenarios and characteristics specific to CAVs, facilitates the application of these AI techniques. The automation focuses on the threat identification and assessment phases of TARA. Machine learning algorithms KNN and Naïve Bayes are evaluated using metrics like accuracy, precision, recall, F1 score, and confusion matrix, achieving 87.5% accuracy. The Ant Colony Optimization (ACO) algorithm predicts attack feasibility ratings, confirming the model’s effectiveness. These metrics demonstrate the AI models’ ability to identify and analyze cybersecurity threats. The results show AI’s potential to transform automotive cybersecurity by automating key TARA stages and providing an efficient framework for threat analysis and risk evaluation.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-Enhanced threat analysis and risk assessment for connected and autonomous vehicles

  • 期刊论文

  • 发表日期：

    2025年6月13日

查看全文
  • Usman Ahmad,
  • Mu Han,
  • Shahid Mahmood

摘要

Threat Analysis and Risk Assessment (TARA) methodologies aid in the early detection of potential threats during the concept and design phases of automotive security engineering process. Their importance is underscored by the relevant industry standards such ISO/SAE 21434 and SAE J3061. While human expertise and involvement are vital for conducting effective TARA, Artificial Intelligence (AI) can enhance the process significantly by automating certain aspects and thus streamlining operations. This study introduces an AI-driven approach to enhance the implementation of TARA. The proposed method leverages machine learning and evolutionary computing algorithms to identify cybersecurity threats in Connected and Autonomous Vehicles (CAVs) through the STRIDE framework. A structured and preprocessed dataset, containing various threat scenarios and characteristics specific to CAVs, facilitates the application of these AI techniques. The automation focuses on the threat identification and assessment phases of TARA. Machine learning algorithms KNN and Naïve Bayes are evaluated using metrics like accuracy, precision, recall, F1 score, and confusion matrix, achieving 87.5% accuracy. The Ant Colony Optimization (ACO) algorithm predicts attack feasibility ratings, confirming the model’s effectiveness. These metrics demonstrate the AI models’ ability to identify and analyze cybersecurity threats. The results show AI’s potential to transform automotive cybersecurity by automating key TARA stages and providing an efficient framework for threat analysis and risk evaluation.