A transformer encoder trained on benign user activity, with reconstruction errors scored by OCSVM, LOF, or Isolation Forest, is reported to achieve state-of-the-art insider threat detection on CERT datasets.
Common sense guide to mitigating insider threats, seventh edition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
User-Based Sequential Modeling with Transformer Encoders for Insider Threat Detection
A transformer encoder trained on benign user activity, with reconstruction errors scored by OCSVM, LOF, or Isolation Forest, is reported to achieve state-of-the-art insider threat detection on CERT datasets.