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

Insider threat detection is getting an increased concern from academia,industry, and governments due to the growing number of malicious insiderincidents. The existing approaches proposed for detecting insider threats stillhave a common shortcoming, which is the high number of false alarms (falsepositives). The challenge in these approaches is that it is essential to detectall anomalous behaviours which belong to a particular threat. To address thisshortcoming, we propose an opportunistic knowledge discovery system, namelyAnyThreat, with the aim to detect any anomalous behaviour in all maliciousinsider threats. We design the AnyThreat system with four components. (1) Afeature engineering component, which constructs community data sets from theactivity logs of a group of users having the same role. (2) An oversamplingcomponent, where we propose a novel oversampling technique named ArtificialMinority Oversampling and Trapper REmoval (AMOTRE). AMOTRE first removes theminority (anomalous) instances that have a high resemblance with normal(majority) instances to reduce the number of false alarms, then itsynthetically oversamples the minority class by shielding the border of themajority class. (3) A class decomposition component, which is introduced tocluster the instances of the majority class into subclasses to weaken theeffect of the majority class without information loss. (4) A classificationcomponent, which applies a classification method on the subclasses to achieve abetter separation between the majority class(es) and the minority class(es).AnyThreat is evaluated on synthetic data sets generated by Carnegie MellonUniversity. It detects approximately 87.5% of malicious insider threats, andachieves the minimum of false positives=3.36%.

AnyThreat: An Opportunistic Knowledge Discovery Approach to Insider Threat Detection