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

The detection of malware is a critical task for the protection of computingenvironments. This task often requires extremely low false positive rates (FPR)of 0.01% or even lower, for which modern machine learning has no readilyavailable tools. We introduce the first broad investigation of the use ofuncertainty for malware detection across multiple datasets, models, and featuretypes. We show how ensembling and Bayesian treatments of machine learningmethods for static malware detection allow for improved identification of modelerrors, uncovering of new malware families, and predictive performance underextreme false positive constraints. In particular, we improve the true positiverate (TPR) at an actual realized FPR of 1e-5 from an expected 0.69 for previousmethods to 0.80 on the best performing model class on the Sophos industry scaledataset. We additionally demonstrate how previous works have used an evaluationprotocol that can lead to misleading results.

Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraints