Scholarlink

Intelligent mechanisms implemented in autonomous vehicles, such as proactive driving assist and pre-collision alerts reduce traffic accidents. However, verifying their correct functionality is difficult due to complex interactions with the environment. This problem is exacerbated in adversarial conditions, where an attacker can control the environment surrounding autonomous vehicles to exploit any vulnerabilities. To preemptively identify vulnerabilities in these systems, in this paper, we implement a scenario-based framework with a formal method to identify the impact of malicious drivers interacting with autonomous vehicles.

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

D4: Dynamic Data-Driven Discovery of Adversarial Vehicle Maneuvers

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Carlos Hernandez,
  • Diego Ortiz Barbosa,
  • Zengxiang Lei,
  • Luis Burbano,
  • Younghee Park,
  • Satish Ukkusuri,
  • Alvaro A. Cardenas

摘要

Intelligent mechanisms implemented in autonomous vehicles, such as proactive driving assist and pre-collision alerts reduce traffic accidents. However, verifying their correct functionality is difficult due to complex interactions with the environment. This problem is exacerbated in adversarial conditions, where an attacker can control the environment surrounding autonomous vehicles to exploit any vulnerabilities. To preemptively identify vulnerabilities in these systems, in this paper, we implement a scenario-based framework with a formal method to identify the impact of malicious drivers interacting with autonomous vehicles.