A set-partitioned Isolation Forest variant detects synthetic network scan anomalies at IP level, with best results on unusual port-service pairings but modest precision on volume spikes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
siForest: Detecting Network Anomalies with Set-Structured Isolation Forest
A set-partitioned Isolation Forest variant detects synthetic network scan anomalies at IP level, with best results on unusual port-service pairings but modest precision on volume spikes.