English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

To enable safe and reliable decision-making, autonomous vehicles (AVs) feedsensor data to perception algorithms to understand the environment. Sensorfusion with multi-frame tracking is becoming increasingly popular for detecting3D objects. Thus, in this work, we perform an analysis of camera-LiDAR fusion,in the AV context, under LiDAR spoofing attacks. Recently, LiDAR-onlyperception was shown vulnerable to LiDAR spoofing attacks; however, wedemonstrate these attacks are not capable of disrupting camera-LiDAR fusion. Wethen define a novel, context-aware attack: frustum attack, and show that out of8 widely used perception algorithms - across 3 architectures of LiDAR-only and3 architectures of camera-LiDAR fusion - all are significantly vulnerable tothe frustum attack. In addition, we demonstrate that the frustum attack isstealthy to existing defenses against LiDAR spoofing as it preservesconsistencies between camera and LiDAR semantics. Finally, we show that thefrustum attack can be exercised consistently over time to form stealthylongitudinal attack sequences, compromising the tracking module and creatingadverse outcomes on end-to-end AV control.

Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehicles