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

In high-level Autonomous Driving (AD) systems, behavioral planning is incharge of making high-level driving decisions such as cruising and stopping,and thus highly securitycritical. In this work, we perform the first systematicstudy of semantic security vulnerabilities specific to overly-conservative ADbehavioral planning behaviors, i.e., those that can cause failed orsignificantly-degraded mission performance, which can be critical for ADservices such as robo-taxi/delivery. We call them semantic Denial-of-Service(DoS) vulnerabilities, which we envision to be most generally exposed inpractical AD systems due to the tendency for conservativeness to avoid safetyincidents. To achieve high practicality and realism, we assume that theattacker can only introduce seemingly-benign external physical objects to thedriving environment, e.g., off-road dumped cardboard boxes.  To systematically discover such vulnerabilities, we design PlanFuzz, a noveldynamic testing approach that addresses various problem-specific designchallenges. Specifically, we propose and identify planning invariants as noveltesting oracles, and design new input generation to systematically enforceproblemspecific constraints for attacker-introduced physical objects. We alsodesign a novel behavioral planning vulnerability distance metric to effectivelyguide the discovery. We evaluate PlanFuzz on 3 planning implementations frompractical open-source AD systems, and find that it can effectively discover 9previouslyunknown semantic DoS vulnerabilities without false positives. We findall our new designs necessary, as without each design, statisticallysignificant performance drops are generally observed. We further performexploitation case studies using simulation and real-vehicle traces. We discussroot causes and potential fixes.

Too Afraid to Drive: Systematic Discovery of Semantic DoS Vulnerability in Autonomous Driving Planning under Physical-World Attacks