arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.13992cs.CRcs.AI
收藏

基于可达性分析的自主车辆物理后门触发器激活

Physical Backdoor Trigger Activation of Autonomous Vehicle using Reachability Analysis

New York University Abu Dhabi(纽约大学阿布扎比分校);Tandon School of Engineering, New York University(纽约大学坦登工程学院)

Wenqing Li, Yue Wang, Muhammad Shafique, Saif Eddin Jabari

摘要:

最近的研究表明,自动驾驶汽车(AV)可以被隐藏的后门操纵,导致它们在被物理触发器激活时执行有害的操作。然而,目前还不清楚如何在遵守交通原则的情况下激活这些触发器。了解动态交通环境中的这种脆弱性至关重要。这项工作解决了这一差距,提出物理触发激活作为一个可达性问题的受控动态系统。我们的技术确定交通系统中的安全关键区域,在那里可以达到事故的触发条件,并提供了如何达到这些条件的预期轨迹。典型交通场景的测试表明,该系统可以成功地驱动到触发条件,激活率接近100%。我们的方法受益于识别AV漏洞和实现有效的安全策略。

英文摘要:

Recent studies reveal that Autonomous Vehicles (AVs) can be manipulated by hidden backdoors, causing them to perform harmful actions when activated by physical triggers. However, it is still unclear how these triggers can be activated while adhering to traffic principles. Understanding this vulnerability in a dynamic traffic environment is crucial. This work addresses this gap by presenting physical trigger activation as a reachability problem of controlled dynamic system. Our technique identifies security-critical areas in traffic systems where trigger conditions for accidents can be reached, and provides intended trajectories for how those conditions can be reached. Testing on typical traffic scenarios showed the system can be successfully driven to trigger conditions with near 100% activation rate. Our method benefits from identifying AV vulnerability and enabling effective safety strategies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑