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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In the development of advanced driver-assistance systems (ADAS) andautonomous vehicles, machine learning techniques that are based on deep neuralnetworks (DNNs) have been widely used for vehicle perception. These techniquesoffer significant improvement on average perception accuracy over traditionalmethods, however, have been shown to be susceptible to adversarial attacks,where small perturbations in the input may cause significant errors in theperception results and lead to system failure. Most prior works addressing suchadversarial attacks focus only on the sensing and perception modules. In thiswork, we propose an end-to-end approach that addresses the impact ofadversarial attacks throughout perception, planning, and control modules. Inparticular, we choose a target ADAS application, the automated lane centeringsystem in OpenPilot, quantify the perception uncertainty under adversarialattacks, and design a robust planning and control module accordingly based onthe uncertainty analysis. We evaluate our proposed approach using both thepublic dataset and production-grade autonomous driving simulator. Theexperiment results demonstrate that our approach can effectively mitigate theimpact of adversarial attacks and can achieve 55% to 90% improvement over theoriginal OpenPilot.

End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering