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 order to support a variety of missions and deal with different flightenvironments, drone control programs typically provide configurable controlparameters. However, such a flexibility introduces vulnerabilities. One suchvulnerability, referred to as range specification bugs, has been recentlyidentified. The vulnerability originates from the fact that even though eachindividual parameter receives a value in the recommended value range, certaincombinations of parameter values may affect the drone physical stability. Inthis paper we develop a novel learning-guided search system to find suchcombinations, that we refer to as incorrect configurations. Our system appliesmetaheuristic search algorithms mutating configurations to detect theconfiguration parameters that have values driving the drone to unstablephysical states. To guide the mutations, our system leverages a machinelearning predictor as the fitness evaluator. Finally, by utilizingmulti-objective optimization, our system returns the feasible ranges based onthe mutation search results. Because in our system the mutations are guided bya predictor, evaluating the parameter configurations does not requirerealistic/simulation executions. Therefore, our system supports a comprehensiveand yet efficient detection of incorrect configurations. We have carried out anexperimental evaluation of our system. The evaluation results show that thesystem successfully reports potentially incorrect configurations, of which over85% lead to actual unstable physical states.

Control Parameters Considered Harmful: Detecting Range Specification Bugs in Drone Configuration Modules via Learning-Guided Search