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

Deep Reinforcement Learning (DRL) enhances the efficiency of AutonomousVehicles (AV), but also makes them susceptible to backdoor attacks that canresult in traffic congestion or collisions. Backdoor functionality is typicallyincorporated by contaminating training datasets with covert malicious data tomaintain high precision on genuine inputs while inducing the desired(malicious) outputs for specific inputs chosen by adversaries. Current defensesagainst backdoors mainly focus on image classification using image-basedfeatures, which cannot be readily transferred to the regression task ofDRL-based AV controllers since the inputs are continuous sensor data, i.e., thecombinations of velocity and distance of AV and its surrounding vehicles. Ourproposed method adds well-designed noise to the input to neutralize backdoors.The approach involves learning an optimal smoothing (noise) distribution topreserve the normal functionality of genuine inputs while neutralizingbackdoors. By doing so, the resulting model is expected to be more resilientagainst backdoor attacks while maintaining high accuracy on genuine inputs. Theeffectiveness of the proposed method is verified on a simulated traffic systembased on a microscopic traffic simulator, where experimental results showcasethat the smoothed traffic controller can neutralize all trigger samples andmaintain the performance of relieving traffic congestion

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems