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

Adaptive Cruise Control (ACC) is a widely used driver assistance technologyfor maintaining the desired speed and safe distance to the leading vehicle.This paper evaluates the security of the deep neural network (DNN) based ACCsystems under runtime stealthy perception attacks that strategically injectperturbations into camera data to cause forward collisions. We present acontext-aware strategy for the selection of the most critical times fortriggering the attacks and a novel optimization-based method for the adaptivegeneration of image perturbations at runtime. We evaluate the effectiveness ofthe proposed attack using a publicly available driving dataset, an actualvehicle, and a realistic simulation platform with the control software from aproduction ACC system, a physical-world driving simulator, and interventions bythe human driver and safety features such as Advanced Emergency Braking System(AEBS). Experimental results show that the proposed attack achieves 142.9 timeshigher success rate in causing hazards and 89.6% higher evasion rate thanbaselines while being stealthy and robust to real-world factors and dynamicchanges in the environment. This study highlights the role of human drivers andbasic safety mechanisms in preventing attacks.

Runtime Stealthy Perception Attacks against DNN-based Adaptive Cruise Control Systems