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

Autonomous Vehicles (AVs) increasingly use LiDAR-based object detectionsystems to perceive other vehicles and pedestrians on the road. While existingattacks on LiDAR-based autonomous driving architectures focus on lowering theconfidence score of AV object detection models to induce obstacle misdetection,our research discovers how to leverage laser-based spoofing techniques toselectively remove the LiDAR point cloud data of genuine obstacles at thesensor level before being used as input to the AV perception. The ablation ofthis critical LiDAR information causes autonomous driving obstacle detectors tofail to identify and locate obstacles and, consequently, induces AVs to makedangerous automatic driving decisions. In this paper, we present a methodinvisible to the human eye that hides objects and deceives autonomous vehicles'obstacle detectors by exploiting inherent automatic transformation andfiltering processes of LiDAR sensor data integrated with autonomous drivingframeworks. We call such attacks Physical Removal Attacks (PRA), and wedemonstrate their effectiveness against three popular AV obstacle detectors(Apollo, Autoware, PointPillars), and we achieve 45{\deg} attack capability. Weevaluate the attack impact on three fusion models (Frustum-ConvNet, AVOD, andIntegrated-Semantic Level Fusion) and the consequences on the driving decisionusing LGSVL, an industry-grade simulator. In our moving vehicle scenarios, weachieve a 92.7% success rate removing 90\% of a target obstacle's cloud points.Finally, we demonstrate the attack's success against two popular defensesagainst spoofing and object hiding attacks and discuss two enhanced defensestrategies to mitigate our attack.

You Can't See Me: Physical Removal Attacks on LiDAR-based Autonomous Vehicles Driving Frameworks