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

Machine learning for malware classification shows encouraging results, butreal deployments suffer from performance degradation as malware authors adapttheir techniques to evade detection. This phenomenon, known as concept drift,occurs as new malware examples evolve and become less and less like theoriginal training examples. One promising method to cope with concept drift isclassification with rejection in which examples that are likely to bemisclassified are instead quarantined until they can be expertly analyzed.  We propose TRANSCENDENT, a rejection framework built on Transcend, a recentlyproposed strategy based on conformal prediction theory. In particular, weprovide a formal treatment of Transcend, enabling us to refine conformalevaluation theory -- its underlying statistical engine -- and gain a betterunderstanding of the theoretical reasons for its effectiveness. In the process,we develop two additional conformal evaluators that match or surpass theperformance of the original while significantly decreasing the computationaloverhead. We evaluate TRANSCENDENT on a malware dataset spanning 5 years thatremoves sources of experimental bias present in the original evaluation.TRANSCENDENT outperforms state-of-the-art approaches while generalizing acrossdifferent malware domains and classifiers.  To further assist practitioners, we determine the optimal operationalsettings for a TRANSCENDENT deployment and show how it can be applied to manypopular learning algorithms. These insights support both old and new empiricalfindings, making Transcend a sound and practical solution for the first time.To this end, we release TRANSCENDENT as open source, to aid the adoption ofrejection strategies by the security community.

Transcending Transcend: Revisiting Malware Classification in the Presence of Concept Drift