Securing Autonomous Vehicles Under Partial-Information Cyber Attacks on LiDAR Data. (arXiv:2303.03470v1 [cs.CR])

Safety is paramount in autonomous vehicles (AVs). Auto manufacturers have
spent millions of dollars and driven billions of miles to prove AVs are safe.
However, this is ill-suited to answer: what happens to an AV if its data are
adversarially compromised? We design a framework built on security-relevant
metrics to benchmark AVs on longitudinal datasets. We establish the
capabilities of a cyber-level attacker with only access to LiDAR datagrams and
from them derive novel attacks on LiDAR. We demonstrate that …

access attacks auto autonomous autonomous vehicles benchmark capabilities compromised cyber cyber attacks data datasets design framework information lidar metrics partial prove safe safety security under vehicles