Shadow-catcher: looking into shadows to detect ghost objects in autonomous vehicle 3D sensing
Author(s)
Hau, Zhongyuan
Demetriou, Soteris
Muñoz-González, Luis
Lupu, Emil C
Type
Chapter
Abstract
LiDAR-driven 3D sensing allows new generations of vehicles to achieve advanced levels of situation awareness. However, recent works have demonstrated that physical adversaries can spoof LiDAR return signals and deceive 3D object detectors to erroneously detect “ghost" objects. Existing defenses are either impractical or focus only on vehicles. Unfortunately, it is easier to spoof smaller objects such as pedestrians and cyclists, but harder to defend against and can have worse safety implications. To address this gap, we introduce Shadow-Catcher, a set of new techniques embodied in an end-to-end prototype to detect both large and small ghost object attacks on 3D detectors. We characterize a new semantically meaningful physical invariant (3D shadows) which Shadow-Catcher leverages for validating objects. Our evaluation on the KITTI dataset shows that Shadow-Catcher consistently achieves more than 94% accuracy in identifying anomalous shadows for vehicles, pedestrians, and cyclists, while it remains robust to a novel class of strong “invalidation” attacks targeting the defense system. Shadow-Catcher can achieve real-time detection, requiring only between 0.003 s–0.021 s on average to process an object in a 3D point cloud on commodity hardware and achieves a 2.17x speedup compared to prior work.
Date Issued
2022-09-30
Date Acceptance
2021-04-08
Citation
2022, pp.691-711
Publisher
Springer International Publishing
Start Page
691
End Page
711
Journal / Book Title
Computer Security – ESORICS 2021
Copyright Statement
© Springer Nature Switzerland AG 2021
Identifier
https://link.springer.com/chapter/10.1007%2F978-3-030-88418-5_33
Source
ESORICS
Subjects
cs.CR
cs.CR
Artificial Intelligence & Image Processing
Publication Status
Published
Date Publish Online
2021-09-30