A heterogeneous stack-classifier on daily summaries from the CERT r4.2 dataset predicts WikiLeaks-style insider leaks at 96.2% accuracy and 0.988 AUC.
Detection and prediction of insider threats to cyber security: a systematic literature review and meta-analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Predicting Malicious Insider Threat Scenarios Using Organizational Data and a Heterogeneous Stack-Classifier
A heterogeneous stack-classifier on daily summaries from the CERT r4.2 dataset predicts WikiLeaks-style insider leaks at 96.2% accuracy and 0.988 AUC.