进行中研究:速成课:(遭受攻击时的)自动驾驶能胜过人类驾驶员吗?
Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers?
AI总结:
该研究针对自动驾驶安全研究的空白,建立务实威胁模型评估其固有风险,分析自动驾驶优势与安全挑战的平衡,为相关研究与实践提供指导,推动自动驾驶安全性与可行性的讨论。
摘要:
近年来,得益于人工智能(AI)的发展,自动驾驶成为了一个备受关注的研究方向。多项研究表明,根据脱离人类驾驶员的自主程度不同,自动驾驶汽车(Autonomous Vehicles, AVs)可通过提升效率减少道路碰撞事故数量,并降低总体燃油排放。然而,针对该主题的安全研究结论不一,且存在一些研究空白。一方面,这些研究往往忽略了AI算法的固有漏洞,而这类漏洞已知会危及自动驾驶系统的安全性。另一方面,针对AI的最常见攻击都基于不切实际的假设,例如能够获取模型参数或训练数据集。因此,在实际应用场景中,自动驾驶是否仍能宣称相较于人类驾驶具备多项优势尚不明确。本文通过梳理自动驾驶汽车的当前研究现状,并建立一个务实的威胁模型,评估了自动驾驶的固有风险。通过分析,我们提出了具体论断,凸显了在真实场景中自动驾驶汽车的优势与潜在安全挑战之间的微妙平衡。我们的评估为提炼核心结论提供了基础,可为自动化流程各阶段的研究人员与从业者提供指导。借此,我们为推进关于自动驾驶在实际应用中的安全性与可行性的讨论贡献了宝贵见解。
英文摘要:
Autonomous driving is a research direction that has gained enormous traction in the last few years thanks to advancements in Artificial Intelligence (AI). Depending on the level of independence from the human driver, several studies show that Autonomous Vehicles (AVs) can reduce the number of on-road crashes and decrease overall fuel emissions by improving efficiency. However, security research on this topic is mixed and presents some gaps. On one hand, these studies often neglect the intrinsic vulnerabilities of AI algorithms, which are known to compromise the security of these systems. On the other, the most prevalent attacks towards AI rely on unrealistic assumptions, such as access to the model parameters or the training dataset. As such, it is unclear if autonomous driving can still claim several advantages over human driving in real-world applications. This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs and establishing a pragmatic threat model. Through our analysis, we develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios. Our evaluation serves as a foundation for providing essential takeaway messages, guiding both researchers and practitioners at various stages of the automation pipeline. In doing so, we contribute valuable insights to advance the discourse on the security and viability of autonomous driving in real-world applications.
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。