Closed-loop framework evaluates attack injection into vehicle reactions
Original title: Attack Injection to Vehicle Reactions: Extensible Closed-Loop Adversarial Evaluation Framework
Built on VaN3Twin, the library has 76 ETSI-adapted attack profiles in nine suites and a labelled dataset.
Researchers present an extensible closed-loop framework on VaN3Twin for studying how falsified vehicle and roadside messages affect application decisions and traffic. Live attack injection and simulated delivery reach receiving applications, whose commands update vehicle movement and later messages. Evaluation confirmed that every profile executed and that every suite produced requests linked to attacked messages. One recorded sequence showed an attacked vehicle later influencing another through an unmodified movement message.
Unconfirmed: Findings come from simulation, not reported roadway incidents.
- The library contains 76 configurable profiles organized into nine attack suites.
- Profiles are adapted to message formats defined by ETSI.
- The dataset links vehicle states and messages to decisions, commands, and outcomes.
- The framework can add attacks, message paths, applications, and logging fields.
- Products
- VaN3Twin
- Organizations
- European Telecommunications Standards Institute
From the original article
1 min read at arxiv.orgAutonomous vehicles can use information exchanged with other vehicles and roadside infrastructure to support driving decisions. However, applications that rely on this information can make unsafe decisions when it is falsified. Studying the resulting traffic effects requires following received information through application decisions, vehicle reactions, and subsequent interactions.
By Mohamed Gaber · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.