Emerging AI Security Threats for Autonomous Cars -- Case Studies

TL;DR

This paper examines emerging AI security threats to autonomous cars, focusing on model extraction attacks, their implications, and potential mitigation strategies to protect sensitive AI models in autonomous vehicle systems.

Contribution

It provides detailed case studies of model extraction attacks on autonomous vehicles and discusses a generic kill-chain for such attacks, highlighting the need for security strategies.

Findings

Model extraction attacks can compromise autonomous vehicle AI models.

Such attacks threaten intellectual property and safety of autonomous systems.

Mitigation strategies are essential to safeguard AI models in autonomous cars.

Abstract

Artificial Intelligence has made a significant contribution to autonomous vehicles, from object detection to path planning. However, AI models require a large amount of sensitive training data and are usually computationally intensive to build. The commercial value of such models motivates attackers to mount various attacks. Adversaries can launch model extraction attacks for monetization purposes or step-ping-stone towards other attacks like model evasion. In specific cases, it even results in destroying brand reputation, differentiation, and value proposition. In addition, IP laws and AI-related legalities are still evolving and are not uniform across countries. We discuss model extraction attacks in detail with two use-cases and a generic kill-chain that can compromise autonomous cars. It is essential to investigate strategies to manage and mitigate the risk of model theft.