Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers?

TL;DR

This paper assesses the security vulnerabilities of autonomous vehicles, analyzing current threats and establishing a realistic threat model to evaluate whether AVs can outperform human drivers amidst security challenges.

Contribution

It provides a pragmatic threat model for autonomous driving, highlighting security risks and offering insights into the balance between AV advantages and vulnerabilities.

Findings

Current AV security research often relies on unrealistic attack assumptions

A pragmatic threat model reveals inherent vulnerabilities in autonomous driving

Guides future research and practice in securing AV systems

Abstract

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.